diff --git a/.nojekyll b/.nojekyll
index ae42b6e64..8410582ab 100644
--- a/.nojekyll
+++ b/.nojekyll
@@ -1 +1 @@
-a2f45856
\ No newline at end of file
+9246de34
\ No newline at end of file
diff --git a/about.html b/about.html
index 970901bf0..1904cb46f 100644
--- a/about.html
+++ b/about.html
@@ -8,7 +8,7 @@
 
 <meta name="keywords" content="open-source, embedded systems, machine learning, tinyML">
 
-<title>Machine Learning Systems for TinyML - About the Book</title>
+<title>MACHINE LEARNING SYSTEMS for TinyML - About the Book</title>
 <style>
 code{white-space: pre-wrap;}
 span.smallcaps{font-variant: small-caps;}
@@ -92,20 +92,20 @@
   <nav id="quarto-sidebar" class="sidebar collapse collapse-horizontal sidebar-navigation floating overflow-auto">
     <div class="pt-lg-2 mt-2 text-left sidebar-header">
     <div class="sidebar-title mb-0 py-0">
-      <a href="./">Machine Learning Systems for TinyML</a> 
+      <a href="./">MACHINE LEARNING SYSTEMS for TinyML</a> 
         <div class="sidebar-tools-main tools-wide">
     <a href="https://github.com/harvard-edge/cs249r_book" rel="" title="Source Code" class="quarto-navigation-tool px-1" aria-label="Source Code"><i class="bi bi-github"></i></a>
     <div class="dropdown">
       <a href="" title="Download" id="quarto-navigation-tool-dropdown-0" class="quarto-navigation-tool dropdown-toggle px-1" data-bs-toggle="dropdown" aria-expanded="false" aria-label="Download"><i class="bi bi-download"></i></a>
       <ul class="dropdown-menu" aria-labelledby="quarto-navigation-tool-dropdown-0">
           <li>
-            <a class="dropdown-item sidebar-tools-main-item" href="./Machine-Learning-Systems-for-TinyML.pdf">
+            <a class="dropdown-item sidebar-tools-main-item" href="./MACHINE-LEARNING-SYSTEMS-for-TinyML.pdf">
               <i class="bi bi-bi-file-pdf pe-1"></i>
             Download PDF
             </a>
           </li>
           <li>
-            <a class="dropdown-item sidebar-tools-main-item" href="./Machine-Learning-Systems-for-TinyML.epub">
+            <a class="dropdown-item sidebar-tools-main-item" href="./MACHINE-LEARNING-SYSTEMS-for-TinyML.epub">
               <i class="bi bi-bi-journal pe-1"></i>
             Download ePub
             </a>
@@ -393,6 +393,12 @@ <h1 class="title">About the Book</h1>
     
   </div>
   
+<div>
+  <div class="abstract">
+    <div class="abstract-title">Abstract</div>
+    Machine Learning Systems for TinyML offers comprehensive guidance on deploying machine learning on embedded devices. As edge computing and the Internet of Things proliferate, this textbook provides professionals and students the expertise to implement performant AI on resource-constrained hardware. A unique aspect of this book elucidates the entire machine learning workflow, from data engineering through training, optimization, acceleration, and production deployment. Key topics covered include deep learning and classical ML algorithms for embedded systems, efficient neural network architectures, hardware-aware training techniques, model compression, benchmarking for tinyML, and on-device learning. Additional chapters highlight cutting-edge advances like on-device data generation and crucial considerations around reliability, privacy, security, and responsible AI. With its rigorous approach spanning theory and practice across diverse tinyML application domains like smart homes, wearables, and industrial IoT, the book enables readers to develop specialized knowledge. Using concrete use cases and hands-on examples, readers will learn to apply machine learning to transform embedded and IoT systems. Overall, this indispensable guide provides a research-based foundation for leveraging machine learning in embedded systems.
+  </div>
+</div>
 
 </header>
 
diff --git a/acknowledgements.html b/acknowledgements.html
index f1ab606af..2e215391f 100644
--- a/acknowledgements.html
+++ b/acknowledgements.html
@@ -8,7 +8,7 @@
 
 <meta name="keywords" content="open-source, embedded systems, machine learning, tinyML">
 
-<title>Machine Learning Systems for TinyML - Acknowledgements</title>
+<title>MACHINE LEARNING SYSTEMS for TinyML - Acknowledgements</title>
 <style>
 code{white-space: pre-wrap;}
 span.smallcaps{font-variant: small-caps;}
@@ -92,20 +92,20 @@
   <nav id="quarto-sidebar" class="sidebar collapse collapse-horizontal sidebar-navigation floating overflow-auto">
     <div class="pt-lg-2 mt-2 text-left sidebar-header">
     <div class="sidebar-title mb-0 py-0">
-      <a href="./">Machine Learning Systems for TinyML</a> 
+      <a href="./">MACHINE LEARNING SYSTEMS for TinyML</a> 
         <div class="sidebar-tools-main tools-wide">
     <a href="https://github.com/harvard-edge/cs249r_book" rel="" title="Source Code" class="quarto-navigation-tool px-1" aria-label="Source Code"><i class="bi bi-github"></i></a>
     <div class="dropdown">
       <a href="" title="Download" id="quarto-navigation-tool-dropdown-0" class="quarto-navigation-tool dropdown-toggle px-1" data-bs-toggle="dropdown" aria-expanded="false" aria-label="Download"><i class="bi bi-download"></i></a>
       <ul class="dropdown-menu" aria-labelledby="quarto-navigation-tool-dropdown-0">
           <li>
-            <a class="dropdown-item sidebar-tools-main-item" href="./Machine-Learning-Systems-for-TinyML.pdf">
+            <a class="dropdown-item sidebar-tools-main-item" href="./MACHINE-LEARNING-SYSTEMS-for-TinyML.pdf">
               <i class="bi bi-bi-file-pdf pe-1"></i>
             Download PDF
             </a>
           </li>
           <li>
-            <a class="dropdown-item sidebar-tools-main-item" href="./Machine-Learning-Systems-for-TinyML.epub">
+            <a class="dropdown-item sidebar-tools-main-item" href="./MACHINE-LEARNING-SYSTEMS-for-TinyML.epub">
               <i class="bi bi-bi-journal pe-1"></i>
             Download ePub
             </a>
@@ -383,6 +383,12 @@ <h1 class="title">Acknowledgements</h1>
     
   </div>
   
+<div>
+  <div class="abstract">
+    <div class="abstract-title">Abstract</div>
+    Machine Learning Systems for TinyML offers comprehensive guidance on deploying machine learning on embedded devices. As edge computing and the Internet of Things proliferate, this textbook provides professionals and students the expertise to implement performant AI on resource-constrained hardware. A unique aspect of this book elucidates the entire machine learning workflow, from data engineering through training, optimization, acceleration, and production deployment. Key topics covered include deep learning and classical ML algorithms for embedded systems, efficient neural network architectures, hardware-aware training techniques, model compression, benchmarking for tinyML, and on-device learning. Additional chapters highlight cutting-edge advances like on-device data generation and crucial considerations around reliability, privacy, security, and responsible AI. With its rigorous approach spanning theory and practice across diverse tinyML application domains like smart homes, wearables, and industrial IoT, the book enables readers to develop specialized knowledge. Using concrete use cases and hands-on examples, readers will learn to apply machine learning to transform embedded and IoT systems. Overall, this indispensable guide provides a research-based foundation for leveraging machine learning in embedded systems.
+  </div>
+</div>
 
 </header>
 
diff --git a/ai_for_good.html b/ai_for_good.html
index af7f8cee4..13bf736bd 100644
--- a/ai_for_good.html
+++ b/ai_for_good.html
@@ -8,7 +8,7 @@
 
 <meta name="keywords" content="open-source, embedded systems, machine learning, tinyML">
 
-<title>Machine Learning Systems for TinyML - 18&nbsp; AI for Good</title>
+<title>MACHINE LEARNING SYSTEMS for TinyML - 18&nbsp; AI for Good</title>
 <style>
 code{white-space: pre-wrap;}
 span.smallcaps{font-variant: small-caps;}
@@ -92,20 +92,20 @@
   <nav id="quarto-sidebar" class="sidebar collapse collapse-horizontal sidebar-navigation floating overflow-auto">
     <div class="pt-lg-2 mt-2 text-left sidebar-header">
     <div class="sidebar-title mb-0 py-0">
-      <a href="./">Machine Learning Systems for TinyML</a> 
+      <a href="./">MACHINE LEARNING SYSTEMS for TinyML</a> 
         <div class="sidebar-tools-main tools-wide">
     <a href="https://github.com/harvard-edge/cs249r_book" rel="" title="Source Code" class="quarto-navigation-tool px-1" aria-label="Source Code"><i class="bi bi-github"></i></a>
     <div class="dropdown">
       <a href="" title="Download" id="quarto-navigation-tool-dropdown-0" class="quarto-navigation-tool dropdown-toggle px-1" data-bs-toggle="dropdown" aria-expanded="false" aria-label="Download"><i class="bi bi-download"></i></a>
       <ul class="dropdown-menu" aria-labelledby="quarto-navigation-tool-dropdown-0">
           <li>
-            <a class="dropdown-item sidebar-tools-main-item" href="./Machine-Learning-Systems-for-TinyML.pdf">
+            <a class="dropdown-item sidebar-tools-main-item" href="./MACHINE-LEARNING-SYSTEMS-for-TinyML.pdf">
               <i class="bi bi-bi-file-pdf pe-1"></i>
             Download PDF
             </a>
           </li>
           <li>
-            <a class="dropdown-item sidebar-tools-main-item" href="./Machine-Learning-Systems-for-TinyML.epub">
+            <a class="dropdown-item sidebar-tools-main-item" href="./MACHINE-LEARNING-SYSTEMS-for-TinyML.epub">
               <i class="bi bi-bi-journal pe-1"></i>
             Download ePub
             </a>
@@ -399,6 +399,12 @@ <h1 class="title"><span class="chapter-number">18</span>&nbsp; <span class="chap
     
   </div>
   
+<div>
+  <div class="abstract">
+    <div class="abstract-title">Abstract</div>
+    Machine Learning Systems for TinyML offers comprehensive guidance on deploying machine learning on embedded devices. As edge computing and the Internet of Things proliferate, this textbook provides professionals and students the expertise to implement performant AI on resource-constrained hardware. A unique aspect of this book elucidates the entire machine learning workflow, from data engineering through training, optimization, acceleration, and production deployment. Key topics covered include deep learning and classical ML algorithms for embedded systems, efficient neural network architectures, hardware-aware training techniques, model compression, benchmarking for tinyML, and on-device learning. Additional chapters highlight cutting-edge advances like on-device data generation and crucial considerations around reliability, privacy, security, and responsible AI. With its rigorous approach spanning theory and practice across diverse tinyML application domains like smart homes, wearables, and industrial IoT, the book enables readers to develop specialized knowledge. Using concrete use cases and hands-on examples, readers will learn to apply machine learning to transform embedded and IoT systems. Overall, this indispensable guide provides a research-based foundation for leveraging machine learning in embedded systems.
+  </div>
+</div>
 
 </header>
 
diff --git a/benchmarking.html b/benchmarking.html
index 0b36194e6..b7cdf09f0 100644
--- a/benchmarking.html
+++ b/benchmarking.html
@@ -8,7 +8,7 @@
 
 <meta name="keywords" content="open-source, embedded systems, machine learning, tinyML">
 
-<title>Machine Learning Systems for TinyML - 12&nbsp; Benchmarking AI</title>
+<title>MACHINE LEARNING SYSTEMS for TinyML - 12&nbsp; Benchmarking AI</title>
 <style>
 code{white-space: pre-wrap;}
 span.smallcaps{font-variant: small-caps;}
@@ -92,20 +92,20 @@
   <nav id="quarto-sidebar" class="sidebar collapse collapse-horizontal sidebar-navigation floating overflow-auto">
     <div class="pt-lg-2 mt-2 text-left sidebar-header">
     <div class="sidebar-title mb-0 py-0">
-      <a href="./">Machine Learning Systems for TinyML</a> 
+      <a href="./">MACHINE LEARNING SYSTEMS for TinyML</a> 
         <div class="sidebar-tools-main tools-wide">
     <a href="https://github.com/harvard-edge/cs249r_book" rel="" title="Source Code" class="quarto-navigation-tool px-1" aria-label="Source Code"><i class="bi bi-github"></i></a>
     <div class="dropdown">
       <a href="" title="Download" id="quarto-navigation-tool-dropdown-0" class="quarto-navigation-tool dropdown-toggle px-1" data-bs-toggle="dropdown" aria-expanded="false" aria-label="Download"><i class="bi bi-download"></i></a>
       <ul class="dropdown-menu" aria-labelledby="quarto-navigation-tool-dropdown-0">
           <li>
-            <a class="dropdown-item sidebar-tools-main-item" href="./Machine-Learning-Systems-for-TinyML.pdf">
+            <a class="dropdown-item sidebar-tools-main-item" href="./MACHINE-LEARNING-SYSTEMS-for-TinyML.pdf">
               <i class="bi bi-bi-file-pdf pe-1"></i>
             Download PDF
             </a>
           </li>
           <li>
-            <a class="dropdown-item sidebar-tools-main-item" href="./Machine-Learning-Systems-for-TinyML.epub">
+            <a class="dropdown-item sidebar-tools-main-item" href="./MACHINE-LEARNING-SYSTEMS-for-TinyML.epub">
               <i class="bi bi-bi-journal pe-1"></i>
             Download ePub
             </a>
@@ -398,6 +398,12 @@ <h1 class="title"><span class="chapter-number">12</span>&nbsp; <span class="chap
     
   </div>
   
+<div>
+  <div class="abstract">
+    <div class="abstract-title">Abstract</div>
+    Machine Learning Systems for TinyML offers comprehensive guidance on deploying machine learning on embedded devices. As edge computing and the Internet of Things proliferate, this textbook provides professionals and students the expertise to implement performant AI on resource-constrained hardware. A unique aspect of this book elucidates the entire machine learning workflow, from data engineering through training, optimization, acceleration, and production deployment. Key topics covered include deep learning and classical ML algorithms for embedded systems, efficient neural network architectures, hardware-aware training techniques, model compression, benchmarking for tinyML, and on-device learning. Additional chapters highlight cutting-edge advances like on-device data generation and crucial considerations around reliability, privacy, security, and responsible AI. With its rigorous approach spanning theory and practice across diverse tinyML application domains like smart homes, wearables, and industrial IoT, the book enables readers to develop specialized knowledge. Using concrete use cases and hands-on examples, readers will learn to apply machine learning to transform embedded and IoT systems. Overall, this indispensable guide provides a research-based foundation for leveraging machine learning in embedded systems.
+  </div>
+</div>
 
 </header>
 
diff --git a/case_studies.html b/case_studies.html
index 0f52c3713..4be113eb9 100644
--- a/case_studies.html
+++ b/case_studies.html
@@ -8,7 +8,7 @@
 
 <meta name="keywords" content="open-source, embedded systems, machine learning, tinyML">
 
-<title>Machine Learning Systems for TinyML - Appendix F: Case Studies</title>
+<title>MACHINE LEARNING SYSTEMS for TinyML - Appendix F: Case Studies</title>
 <style>
 code{white-space: pre-wrap;}
 span.smallcaps{font-variant: small-caps;}
@@ -91,20 +91,20 @@
   <nav id="quarto-sidebar" class="sidebar collapse collapse-horizontal sidebar-navigation floating overflow-auto">
     <div class="pt-lg-2 mt-2 text-left sidebar-header">
     <div class="sidebar-title mb-0 py-0">
-      <a href="./">Machine Learning Systems for TinyML</a> 
+      <a href="./">MACHINE LEARNING SYSTEMS for TinyML</a> 
         <div class="sidebar-tools-main tools-wide">
     <a href="https://github.com/harvard-edge/cs249r_book" rel="" title="Source Code" class="quarto-navigation-tool px-1" aria-label="Source Code"><i class="bi bi-github"></i></a>
     <div class="dropdown">
       <a href="" title="Download" id="quarto-navigation-tool-dropdown-0" class="quarto-navigation-tool dropdown-toggle px-1" data-bs-toggle="dropdown" aria-expanded="false" aria-label="Download"><i class="bi bi-download"></i></a>
       <ul class="dropdown-menu" aria-labelledby="quarto-navigation-tool-dropdown-0">
           <li>
-            <a class="dropdown-item sidebar-tools-main-item" href="./Machine-Learning-Systems-for-TinyML.pdf">
+            <a class="dropdown-item sidebar-tools-main-item" href="./MACHINE-LEARNING-SYSTEMS-for-TinyML.pdf">
               <i class="bi bi-bi-file-pdf pe-1"></i>
             Download PDF
             </a>
           </li>
           <li>
-            <a class="dropdown-item sidebar-tools-main-item" href="./Machine-Learning-Systems-for-TinyML.epub">
+            <a class="dropdown-item sidebar-tools-main-item" href="./MACHINE-LEARNING-SYSTEMS-for-TinyML.epub">
               <i class="bi bi-bi-journal pe-1"></i>
             Download ePub
             </a>
@@ -382,6 +382,12 @@ <h1 class="title">Appendix F: Case Studies</h1>
     
   </div>
   
+<div>
+  <div class="abstract">
+    <div class="abstract-title">Abstract</div>
+    Machine Learning Systems for TinyML offers comprehensive guidance on deploying machine learning on embedded devices. As edge computing and the Internet of Things proliferate, this textbook provides professionals and students the expertise to implement performant AI on resource-constrained hardware. A unique aspect of this book elucidates the entire machine learning workflow, from data engineering through training, optimization, acceleration, and production deployment. Key topics covered include deep learning and classical ML algorithms for embedded systems, efficient neural network architectures, hardware-aware training techniques, model compression, benchmarking for tinyML, and on-device learning. Additional chapters highlight cutting-edge advances like on-device data generation and crucial considerations around reliability, privacy, security, and responsible AI. With its rigorous approach spanning theory and practice across diverse tinyML application domains like smart homes, wearables, and industrial IoT, the book enables readers to develop specialized knowledge. Using concrete use cases and hands-on examples, readers will learn to apply machine learning to transform embedded and IoT systems. Overall, this indispensable guide provides a research-based foundation for leveraging machine learning in embedded systems.
+  </div>
+</div>
 
 </header>
 
diff --git a/community.html b/community.html
index abdc59b89..b1908225f 100644
--- a/community.html
+++ b/community.html
@@ -8,7 +8,7 @@
 
 <meta name="keywords" content="open-source, embedded systems, machine learning, tinyML">
 
-<title>Machine Learning Systems for TinyML - Appendix E: Communities</title>
+<title>MACHINE LEARNING SYSTEMS for TinyML - Appendix E: Communities</title>
 <style>
 code{white-space: pre-wrap;}
 span.smallcaps{font-variant: small-caps;}
@@ -92,20 +92,20 @@
   <nav id="quarto-sidebar" class="sidebar collapse collapse-horizontal sidebar-navigation floating overflow-auto">
     <div class="pt-lg-2 mt-2 text-left sidebar-header">
     <div class="sidebar-title mb-0 py-0">
-      <a href="./">Machine Learning Systems for TinyML</a> 
+      <a href="./">MACHINE LEARNING SYSTEMS for TinyML</a> 
         <div class="sidebar-tools-main tools-wide">
     <a href="https://github.com/harvard-edge/cs249r_book" rel="" title="Source Code" class="quarto-navigation-tool px-1" aria-label="Source Code"><i class="bi bi-github"></i></a>
     <div class="dropdown">
       <a href="" title="Download" id="quarto-navigation-tool-dropdown-0" class="quarto-navigation-tool dropdown-toggle px-1" data-bs-toggle="dropdown" aria-expanded="false" aria-label="Download"><i class="bi bi-download"></i></a>
       <ul class="dropdown-menu" aria-labelledby="quarto-navigation-tool-dropdown-0">
           <li>
-            <a class="dropdown-item sidebar-tools-main-item" href="./Machine-Learning-Systems-for-TinyML.pdf">
+            <a class="dropdown-item sidebar-tools-main-item" href="./MACHINE-LEARNING-SYSTEMS-for-TinyML.pdf">
               <i class="bi bi-bi-file-pdf pe-1"></i>
             Download PDF
             </a>
           </li>
           <li>
-            <a class="dropdown-item sidebar-tools-main-item" href="./Machine-Learning-Systems-for-TinyML.epub">
+            <a class="dropdown-item sidebar-tools-main-item" href="./MACHINE-LEARNING-SYSTEMS-for-TinyML.epub">
               <i class="bi bi-bi-journal pe-1"></i>
             Download ePub
             </a>
@@ -392,6 +392,12 @@ <h1 class="title">Appendix E: Communities</h1>
     
   </div>
   
+<div>
+  <div class="abstract">
+    <div class="abstract-title">Abstract</div>
+    Machine Learning Systems for TinyML offers comprehensive guidance on deploying machine learning on embedded devices. As edge computing and the Internet of Things proliferate, this textbook provides professionals and students the expertise to implement performant AI on resource-constrained hardware. A unique aspect of this book elucidates the entire machine learning workflow, from data engineering through training, optimization, acceleration, and production deployment. Key topics covered include deep learning and classical ML algorithms for embedded systems, efficient neural network architectures, hardware-aware training techniques, model compression, benchmarking for tinyML, and on-device learning. Additional chapters highlight cutting-edge advances like on-device data generation and crucial considerations around reliability, privacy, security, and responsible AI. With its rigorous approach spanning theory and practice across diverse tinyML application domains like smart homes, wearables, and industrial IoT, the book enables readers to develop specialized knowledge. Using concrete use cases and hands-on examples, readers will learn to apply machine learning to transform embedded and IoT systems. Overall, this indispensable guide provides a research-based foundation for leveraging machine learning in embedded systems.
+  </div>
+</div>
 
 </header>
 
diff --git a/contributors.html b/contributors.html
index 18b3411ac..d8b458867 100644
--- a/contributors.html
+++ b/contributors.html
@@ -8,7 +8,7 @@
 
 <meta name="keywords" content="open-source, embedded systems, machine learning, tinyML">
 
-<title>Machine Learning Systems for TinyML - Contributors</title>
+<title>MACHINE LEARNING SYSTEMS for TinyML - Contributors</title>
 <style>
 code{white-space: pre-wrap;}
 span.smallcaps{font-variant: small-caps;}
@@ -92,20 +92,20 @@
   <nav id="quarto-sidebar" class="sidebar collapse collapse-horizontal sidebar-navigation floating overflow-auto">
     <div class="pt-lg-2 mt-2 text-left sidebar-header">
     <div class="sidebar-title mb-0 py-0">
-      <a href="./">Machine Learning Systems for TinyML</a> 
+      <a href="./">MACHINE LEARNING SYSTEMS for TinyML</a> 
         <div class="sidebar-tools-main tools-wide">
     <a href="https://github.com/harvard-edge/cs249r_book" rel="" title="Source Code" class="quarto-navigation-tool px-1" aria-label="Source Code"><i class="bi bi-github"></i></a>
     <div class="dropdown">
       <a href="" title="Download" id="quarto-navigation-tool-dropdown-0" class="quarto-navigation-tool dropdown-toggle px-1" data-bs-toggle="dropdown" aria-expanded="false" aria-label="Download"><i class="bi bi-download"></i></a>
       <ul class="dropdown-menu" aria-labelledby="quarto-navigation-tool-dropdown-0">
           <li>
-            <a class="dropdown-item sidebar-tools-main-item" href="./Machine-Learning-Systems-for-TinyML.pdf">
+            <a class="dropdown-item sidebar-tools-main-item" href="./MACHINE-LEARNING-SYSTEMS-for-TinyML.pdf">
               <i class="bi bi-bi-file-pdf pe-1"></i>
             Download PDF
             </a>
           </li>
           <li>
-            <a class="dropdown-item sidebar-tools-main-item" href="./Machine-Learning-Systems-for-TinyML.epub">
+            <a class="dropdown-item sidebar-tools-main-item" href="./MACHINE-LEARNING-SYSTEMS-for-TinyML.epub">
               <i class="bi bi-bi-journal pe-1"></i>
             Download ePub
             </a>
@@ -383,6 +383,12 @@ <h1 class="title">Contributors</h1>
     
   </div>
   
+<div>
+  <div class="abstract">
+    <div class="abstract-title">Abstract</div>
+    Machine Learning Systems for TinyML offers comprehensive guidance on deploying machine learning on embedded devices. As edge computing and the Internet of Things proliferate, this textbook provides professionals and students the expertise to implement performant AI on resource-constrained hardware. A unique aspect of this book elucidates the entire machine learning workflow, from data engineering through training, optimization, acceleration, and production deployment. Key topics covered include deep learning and classical ML algorithms for embedded systems, efficient neural network architectures, hardware-aware training techniques, model compression, benchmarking for tinyML, and on-device learning. Additional chapters highlight cutting-edge advances like on-device data generation and crucial considerations around reliability, privacy, security, and responsible AI. With its rigorous approach spanning theory and practice across diverse tinyML application domains like smart homes, wearables, and industrial IoT, the book enables readers to develop specialized knowledge. Using concrete use cases and hands-on examples, readers will learn to apply machine learning to transform embedded and IoT systems. Overall, this indispensable guide provides a research-based foundation for leveraging machine learning in embedded systems.
+  </div>
+</div>
 
 </header>
 
@@ -395,13 +401,13 @@ <h1 class="title">Contributors</h1>
 <tbody>
 <tr>
 <td align="center" valign="top" width="14.28%">
-<a href="https://github.com/mpstewart1"><img src="https://avatars.githubusercontent.com/mpstewart1?s=100" width="100px;" alt="Matthew Stewart"><br><sub><b>Matthew Stewart</b></sub></a><br><a href="https=//github.com/harvard-edge/cs249r_book/commits?author=mpstewart1" title="Documentation">📖</a>
+<a href="https://github.com/ShvetankPrakash"><img src="https://avatars.githubusercontent.com/ShvetankPrakash?s=100" width="100px;" alt="Shvetank Prakash"><br><sub><b>Shvetank Prakash</b></sub></a><br><a href="https=//github.com/harvard-edge/cs249r_book/commits?author=ShvetankPrakash" title="Documentation">📖</a>
 </td>
 <td align="center" valign="top" width="14.28%">
 <a href="https://github.com/jveejay"><img src="https://avatars.githubusercontent.com/jveejay?s=100" width="100px;" alt="Vijay Janapa Reddi"><br><sub><b>Vijay Janapa Reddi</b></sub></a><br><a href="https=//github.com/harvard-edge/cs249r_book/commits?author=jveejay" title="Documentation">📖</a>
 </td>
 <td align="center" valign="top" width="14.28%">
-<a href="https://github.com/ShvetankPrakash"><img src="https://avatars.githubusercontent.com/ShvetankPrakash?s=100" width="100px;" alt="Shvetank Prakash"><br><sub><b>Shvetank Prakash</b></sub></a><br><a href="https=//github.com/harvard-edge/cs249r_book/commits?author=ShvetankPrakash" title="Documentation">📖</a>
+<a href="https://github.com/mpstewart1"><img src="https://avatars.githubusercontent.com/mpstewart1?s=100" width="100px;" alt="Matthew Stewart"><br><sub><b>Matthew Stewart</b></sub></a><br><a href="https=//github.com/harvard-edge/cs249r_book/commits?author=mpstewart1" title="Documentation">📖</a>
 </td>
 <td align="center" valign="top" width="14.28%">
 <a href="https://github.com/uchendui"><img src="https://avatars.githubusercontent.com/uchendui?s=100" width="100px;" alt="Ikechukwu Uchendu"><br><sub><b>Ikechukwu Uchendu</b></sub></a><br><a href="https=//github.com/harvard-edge/cs249r_book/commits?author=uchendui" title="Documentation">📖</a>
diff --git a/copyright.html b/copyright.html
index 14b338315..8bd7067da 100644
--- a/copyright.html
+++ b/copyright.html
@@ -8,7 +8,7 @@
 
 <meta name="keywords" content="open-source, embedded systems, machine learning, tinyML">
 
-<title>Machine Learning Systems for TinyML - Copyright</title>
+<title>MACHINE LEARNING SYSTEMS for TinyML - Copyright</title>
 <style>
 code{white-space: pre-wrap;}
 span.smallcaps{font-variant: small-caps;}
@@ -92,20 +92,20 @@
   <nav id="quarto-sidebar" class="sidebar collapse collapse-horizontal sidebar-navigation floating overflow-auto">
     <div class="pt-lg-2 mt-2 text-left sidebar-header">
     <div class="sidebar-title mb-0 py-0">
-      <a href="./">Machine Learning Systems for TinyML</a> 
+      <a href="./">MACHINE LEARNING SYSTEMS for TinyML</a> 
         <div class="sidebar-tools-main tools-wide">
     <a href="https://github.com/harvard-edge/cs249r_book" rel="" title="Source Code" class="quarto-navigation-tool px-1" aria-label="Source Code"><i class="bi bi-github"></i></a>
     <div class="dropdown">
       <a href="" title="Download" id="quarto-navigation-tool-dropdown-0" class="quarto-navigation-tool dropdown-toggle px-1" data-bs-toggle="dropdown" aria-expanded="false" aria-label="Download"><i class="bi bi-download"></i></a>
       <ul class="dropdown-menu" aria-labelledby="quarto-navigation-tool-dropdown-0">
           <li>
-            <a class="dropdown-item sidebar-tools-main-item" href="./Machine-Learning-Systems-for-TinyML.pdf">
+            <a class="dropdown-item sidebar-tools-main-item" href="./MACHINE-LEARNING-SYSTEMS-for-TinyML.pdf">
               <i class="bi bi-bi-file-pdf pe-1"></i>
             Download PDF
             </a>
           </li>
           <li>
-            <a class="dropdown-item sidebar-tools-main-item" href="./Machine-Learning-Systems-for-TinyML.epub">
+            <a class="dropdown-item sidebar-tools-main-item" href="./MACHINE-LEARNING-SYSTEMS-for-TinyML.epub">
               <i class="bi bi-bi-journal pe-1"></i>
             Download ePub
             </a>
@@ -383,6 +383,12 @@ <h1 class="title">Copyright</h1>
     
   </div>
   
+<div>
+  <div class="abstract">
+    <div class="abstract-title">Abstract</div>
+    Machine Learning Systems for TinyML offers comprehensive guidance on deploying machine learning on embedded devices. As edge computing and the Internet of Things proliferate, this textbook provides professionals and students the expertise to implement performant AI on resource-constrained hardware. A unique aspect of this book elucidates the entire machine learning workflow, from data engineering through training, optimization, acceleration, and production deployment. Key topics covered include deep learning and classical ML algorithms for embedded systems, efficient neural network architectures, hardware-aware training techniques, model compression, benchmarking for tinyML, and on-device learning. Additional chapters highlight cutting-edge advances like on-device data generation and crucial considerations around reliability, privacy, security, and responsible AI. With its rigorous approach spanning theory and practice across diverse tinyML application domains like smart homes, wearables, and industrial IoT, the book enables readers to develop specialized knowledge. Using concrete use cases and hands-on examples, readers will learn to apply machine learning to transform embedded and IoT systems. Overall, this indispensable guide provides a research-based foundation for leveraging machine learning in embedded systems.
+  </div>
+</div>
 
 </header>
 
diff --git a/data_engineering.html b/data_engineering.html
index 06314a4b7..d7dff6837 100644
--- a/data_engineering.html
+++ b/data_engineering.html
@@ -8,7 +8,7 @@
 
 <meta name="keywords" content="open-source, embedded systems, machine learning, tinyML">
 
-<title>Machine Learning Systems for TinyML - 6&nbsp; Data Engineering</title>
+<title>MACHINE LEARNING SYSTEMS for TinyML - 6&nbsp; Data Engineering</title>
 <style>
 code{white-space: pre-wrap;}
 span.smallcaps{font-variant: small-caps;}
@@ -92,20 +92,20 @@
   <nav id="quarto-sidebar" class="sidebar collapse collapse-horizontal sidebar-navigation floating overflow-auto">
     <div class="pt-lg-2 mt-2 text-left sidebar-header">
     <div class="sidebar-title mb-0 py-0">
-      <a href="./">Machine Learning Systems for TinyML</a> 
+      <a href="./">MACHINE LEARNING SYSTEMS for TinyML</a> 
         <div class="sidebar-tools-main tools-wide">
     <a href="https://github.com/harvard-edge/cs249r_book" rel="" title="Source Code" class="quarto-navigation-tool px-1" aria-label="Source Code"><i class="bi bi-github"></i></a>
     <div class="dropdown">
       <a href="" title="Download" id="quarto-navigation-tool-dropdown-0" class="quarto-navigation-tool dropdown-toggle px-1" data-bs-toggle="dropdown" aria-expanded="false" aria-label="Download"><i class="bi bi-download"></i></a>
       <ul class="dropdown-menu" aria-labelledby="quarto-navigation-tool-dropdown-0">
           <li>
-            <a class="dropdown-item sidebar-tools-main-item" href="./Machine-Learning-Systems-for-TinyML.pdf">
+            <a class="dropdown-item sidebar-tools-main-item" href="./MACHINE-LEARNING-SYSTEMS-for-TinyML.pdf">
               <i class="bi bi-bi-file-pdf pe-1"></i>
             Download PDF
             </a>
           </li>
           <li>
-            <a class="dropdown-item sidebar-tools-main-item" href="./Machine-Learning-Systems-for-TinyML.epub">
+            <a class="dropdown-item sidebar-tools-main-item" href="./MACHINE-LEARNING-SYSTEMS-for-TinyML.epub">
               <i class="bi bi-bi-journal pe-1"></i>
             Download ePub
             </a>
@@ -402,6 +402,12 @@ <h1 class="title"><span class="chapter-number">6</span>&nbsp; <span class="chapt
     
   </div>
   
+<div>
+  <div class="abstract">
+    <div class="abstract-title">Abstract</div>
+    Machine Learning Systems for TinyML offers comprehensive guidance on deploying machine learning on embedded devices. As edge computing and the Internet of Things proliferate, this textbook provides professionals and students the expertise to implement performant AI on resource-constrained hardware. A unique aspect of this book elucidates the entire machine learning workflow, from data engineering through training, optimization, acceleration, and production deployment. Key topics covered include deep learning and classical ML algorithms for embedded systems, efficient neural network architectures, hardware-aware training techniques, model compression, benchmarking for tinyML, and on-device learning. Additional chapters highlight cutting-edge advances like on-device data generation and crucial considerations around reliability, privacy, security, and responsible AI. With its rigorous approach spanning theory and practice across diverse tinyML application domains like smart homes, wearables, and industrial IoT, the book enables readers to develop specialized knowledge. Using concrete use cases and hands-on examples, readers will learn to apply machine learning to transform embedded and IoT systems. Overall, this indispensable guide provides a research-based foundation for leveraging machine learning in embedded systems.
+  </div>
+</div>
 
 </header>
 
diff --git a/dedication.html b/dedication.html
index e15785f97..c0a12f44c 100644
--- a/dedication.html
+++ b/dedication.html
@@ -8,7 +8,7 @@
 
 <meta name="keywords" content="open-source, embedded systems, machine learning, tinyML">
 
-<title>Machine Learning Systems for TinyML - Dedication</title>
+<title>MACHINE LEARNING SYSTEMS for TinyML - Dedication</title>
 <style>
 code{white-space: pre-wrap;}
 span.smallcaps{font-variant: small-caps;}
@@ -92,20 +92,20 @@
   <nav id="quarto-sidebar" class="sidebar collapse collapse-horizontal sidebar-navigation floating overflow-auto">
     <div class="pt-lg-2 mt-2 text-left sidebar-header">
     <div class="sidebar-title mb-0 py-0">
-      <a href="./">Machine Learning Systems for TinyML</a> 
+      <a href="./">MACHINE LEARNING SYSTEMS for TinyML</a> 
         <div class="sidebar-tools-main tools-wide">
     <a href="https://github.com/harvard-edge/cs249r_book" rel="" title="Source Code" class="quarto-navigation-tool px-1" aria-label="Source Code"><i class="bi bi-github"></i></a>
     <div class="dropdown">
       <a href="" title="Download" id="quarto-navigation-tool-dropdown-0" class="quarto-navigation-tool dropdown-toggle px-1" data-bs-toggle="dropdown" aria-expanded="false" aria-label="Download"><i class="bi bi-download"></i></a>
       <ul class="dropdown-menu" aria-labelledby="quarto-navigation-tool-dropdown-0">
           <li>
-            <a class="dropdown-item sidebar-tools-main-item" href="./Machine-Learning-Systems-for-TinyML.pdf">
+            <a class="dropdown-item sidebar-tools-main-item" href="./MACHINE-LEARNING-SYSTEMS-for-TinyML.pdf">
               <i class="bi bi-bi-file-pdf pe-1"></i>
             Download PDF
             </a>
           </li>
           <li>
-            <a class="dropdown-item sidebar-tools-main-item" href="./Machine-Learning-Systems-for-TinyML.epub">
+            <a class="dropdown-item sidebar-tools-main-item" href="./MACHINE-LEARNING-SYSTEMS-for-TinyML.epub">
               <i class="bi bi-bi-journal pe-1"></i>
             Download ePub
             </a>
@@ -383,6 +383,12 @@ <h1 class="title">Dedication</h1>
     
   </div>
   
+<div>
+  <div class="abstract">
+    <div class="abstract-title">Abstract</div>
+    Machine Learning Systems for TinyML offers comprehensive guidance on deploying machine learning on embedded devices. As edge computing and the Internet of Things proliferate, this textbook provides professionals and students the expertise to implement performant AI on resource-constrained hardware. A unique aspect of this book elucidates the entire machine learning workflow, from data engineering through training, optimization, acceleration, and production deployment. Key topics covered include deep learning and classical ML algorithms for embedded systems, efficient neural network architectures, hardware-aware training techniques, model compression, benchmarking for tinyML, and on-device learning. Additional chapters highlight cutting-edge advances like on-device data generation and crucial considerations around reliability, privacy, security, and responsible AI. With its rigorous approach spanning theory and practice across diverse tinyML application domains like smart homes, wearables, and industrial IoT, the book enables readers to develop specialized knowledge. Using concrete use cases and hands-on examples, readers will learn to apply machine learning to transform embedded and IoT systems. Overall, this indispensable guide provides a research-based foundation for leveraging machine learning in embedded systems.
+  </div>
+</div>
 
 </header>
 
diff --git a/dl_primer.html b/dl_primer.html
index 9afd3a203..343ded242 100644
--- a/dl_primer.html
+++ b/dl_primer.html
@@ -8,7 +8,7 @@
 
 <meta name="keywords" content="open-source, embedded systems, machine learning, tinyML">
 
-<title>Machine Learning Systems for TinyML - 3&nbsp; Deep Learning Primer</title>
+<title>MACHINE LEARNING SYSTEMS for TinyML - 3&nbsp; Deep Learning Primer</title>
 <style>
 code{white-space: pre-wrap;}
 span.smallcaps{font-variant: small-caps;}
@@ -111,20 +111,20 @@
   <nav id="quarto-sidebar" class="sidebar collapse collapse-horizontal sidebar-navigation floating overflow-auto">
     <div class="pt-lg-2 mt-2 text-left sidebar-header">
     <div class="sidebar-title mb-0 py-0">
-      <a href="./">Machine Learning Systems for TinyML</a> 
+      <a href="./">MACHINE LEARNING SYSTEMS for TinyML</a> 
         <div class="sidebar-tools-main tools-wide">
     <a href="https://github.com/harvard-edge/cs249r_book" rel="" title="Source Code" class="quarto-navigation-tool px-1" aria-label="Source Code"><i class="bi bi-github"></i></a>
     <div class="dropdown">
       <a href="" title="Download" id="quarto-navigation-tool-dropdown-0" class="quarto-navigation-tool dropdown-toggle px-1" data-bs-toggle="dropdown" aria-expanded="false" aria-label="Download"><i class="bi bi-download"></i></a>
       <ul class="dropdown-menu" aria-labelledby="quarto-navigation-tool-dropdown-0">
           <li>
-            <a class="dropdown-item sidebar-tools-main-item" href="./Machine-Learning-Systems-for-TinyML.pdf">
+            <a class="dropdown-item sidebar-tools-main-item" href="./MACHINE-LEARNING-SYSTEMS-for-TinyML.pdf">
               <i class="bi bi-bi-file-pdf pe-1"></i>
             Download PDF
             </a>
           </li>
           <li>
-            <a class="dropdown-item sidebar-tools-main-item" href="./Machine-Learning-Systems-for-TinyML.epub">
+            <a class="dropdown-item sidebar-tools-main-item" href="./MACHINE-LEARNING-SYSTEMS-for-TinyML.epub">
               <i class="bi bi-bi-journal pe-1"></i>
             Download ePub
             </a>
@@ -426,6 +426,12 @@ <h1 class="title"><span class="chapter-number">3</span>&nbsp; <span class="chapt
     
   </div>
   
+<div>
+  <div class="abstract">
+    <div class="abstract-title">Abstract</div>
+    Machine Learning Systems for TinyML offers comprehensive guidance on deploying machine learning on embedded devices. As edge computing and the Internet of Things proliferate, this textbook provides professionals and students the expertise to implement performant AI on resource-constrained hardware. A unique aspect of this book elucidates the entire machine learning workflow, from data engineering through training, optimization, acceleration, and production deployment. Key topics covered include deep learning and classical ML algorithms for embedded systems, efficient neural network architectures, hardware-aware training techniques, model compression, benchmarking for tinyML, and on-device learning. Additional chapters highlight cutting-edge advances like on-device data generation and crucial considerations around reliability, privacy, security, and responsible AI. With its rigorous approach spanning theory and practice across diverse tinyML application domains like smart homes, wearables, and industrial IoT, the book enables readers to develop specialized knowledge. Using concrete use cases and hands-on examples, readers will learn to apply machine learning to transform embedded and IoT systems. Overall, this indispensable guide provides a research-based foundation for leveraging machine learning in embedded systems.
+  </div>
+</div>
 
 </header>
 
diff --git a/efficient_ai.html b/efficient_ai.html
index d6be7456c..2c011bc89 100644
--- a/efficient_ai.html
+++ b/efficient_ai.html
@@ -8,7 +8,7 @@
 
 <meta name="keywords" content="open-source, embedded systems, machine learning, tinyML">
 
-<title>Machine Learning Systems for TinyML - 9&nbsp; Efficient AI</title>
+<title>MACHINE LEARNING SYSTEMS for TinyML - 9&nbsp; Efficient AI</title>
 <style>
 code{white-space: pre-wrap;}
 span.smallcaps{font-variant: small-caps;}
@@ -111,20 +111,20 @@
   <nav id="quarto-sidebar" class="sidebar collapse collapse-horizontal sidebar-navigation floating overflow-auto">
     <div class="pt-lg-2 mt-2 text-left sidebar-header">
     <div class="sidebar-title mb-0 py-0">
-      <a href="./">Machine Learning Systems for TinyML</a> 
+      <a href="./">MACHINE LEARNING SYSTEMS for TinyML</a> 
         <div class="sidebar-tools-main tools-wide">
     <a href="https://github.com/harvard-edge/cs249r_book" rel="" title="Source Code" class="quarto-navigation-tool px-1" aria-label="Source Code"><i class="bi bi-github"></i></a>
     <div class="dropdown">
       <a href="" title="Download" id="quarto-navigation-tool-dropdown-0" class="quarto-navigation-tool dropdown-toggle px-1" data-bs-toggle="dropdown" aria-expanded="false" aria-label="Download"><i class="bi bi-download"></i></a>
       <ul class="dropdown-menu" aria-labelledby="quarto-navigation-tool-dropdown-0">
           <li>
-            <a class="dropdown-item sidebar-tools-main-item" href="./Machine-Learning-Systems-for-TinyML.pdf">
+            <a class="dropdown-item sidebar-tools-main-item" href="./MACHINE-LEARNING-SYSTEMS-for-TinyML.pdf">
               <i class="bi bi-bi-file-pdf pe-1"></i>
             Download PDF
             </a>
           </li>
           <li>
-            <a class="dropdown-item sidebar-tools-main-item" href="./Machine-Learning-Systems-for-TinyML.epub">
+            <a class="dropdown-item sidebar-tools-main-item" href="./MACHINE-LEARNING-SYSTEMS-for-TinyML.epub">
               <i class="bi bi-bi-journal pe-1"></i>
             Download ePub
             </a>
@@ -423,6 +423,12 @@ <h1 class="title"><span class="chapter-number">9</span>&nbsp; <span class="chapt
     
   </div>
   
+<div>
+  <div class="abstract">
+    <div class="abstract-title">Abstract</div>
+    Machine Learning Systems for TinyML offers comprehensive guidance on deploying machine learning on embedded devices. As edge computing and the Internet of Things proliferate, this textbook provides professionals and students the expertise to implement performant AI on resource-constrained hardware. A unique aspect of this book elucidates the entire machine learning workflow, from data engineering through training, optimization, acceleration, and production deployment. Key topics covered include deep learning and classical ML algorithms for embedded systems, efficient neural network architectures, hardware-aware training techniques, model compression, benchmarking for tinyML, and on-device learning. Additional chapters highlight cutting-edge advances like on-device data generation and crucial considerations around reliability, privacy, security, and responsible AI. With its rigorous approach spanning theory and practice across diverse tinyML application domains like smart homes, wearables, and industrial IoT, the book enables readers to develop specialized knowledge. Using concrete use cases and hands-on examples, readers will learn to apply machine learning to transform embedded and IoT systems. Overall, this indispensable guide provides a research-based foundation for leveraging machine learning in embedded systems.
+  </div>
+</div>
 
 </header>
 
@@ -464,12 +470,16 @@ <h2 data-number="9.3" class="anchored" data-anchor-id="efficient-model-architect
 <div class="no-row-height column-margin column-container"><div id="ref-he2016deep" class="csl-entry" role="listitem">
 He, Kaiming, Xiangyu Zhang, Shaoqing Ren, and Jian Sun. 2016. <span>“Deep Residual Learning for Image Recognition.”</span> In <em>Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition</em>, 770–78.
 </div></div></section>
-<section id="efficient-model-compression" class="level2" data-number="9.4">
+<section id="efficient-model-compression" class="level2 page-columns page-full" data-number="9.4">
 <h2 data-number="9.4" class="anchored" data-anchor-id="efficient-model-compression"><span class="header-section-number">9.4</span> Efficient Model Compression</h2>
 <p>Model compression methods are very important for bringing deep learning models to devices with limited resources. These techniques reduce the size, energy consumption, and computational demands of models without a significant loss in accuracy. At a high level, the methods can briefly be binned into the following fundamental methods:</p>
-<p><strong>Pruning</strong>: This is akin to trimming the branches of a tree. In pruning, certain weights or even entire neurons are removed from the network, based on specific criteria. This can significantly reduce the model size. There are various strategies, like weight pruning, neuron pruning, and structured pruning.</p>
-<p><strong>Quantization</strong>: Quantization is the process of constraining an input from a large set to output in a smaller set, primarily in deep learning, this means reducing the number of bits that represent the weights and biases of the model. For example, using 16-bit or 8-bit representations instead of 32-bit can reduce model size and speed up computations, with a minor trade-off in accuracy.</p>
-<p><strong>Knowledge Distillation</strong>: Knowledge distillation involves training a smaller model (student) to replicate the behavior of a larger model (teacher). The idea is to transfer the knowledge from the cumbersome model to the lightweight one, so the smaller model attains performance close to its larger counterpart but with significantly fewer parameters.</p>
+<p><strong>Pruning</strong>: This is akin to trimming the branches of a tree. This was first thought of in the <a href="https://proceedings.neurips.cc/paper/1989/file/6c9882bbac1c7093bd25041881277658-Paper.pdf">Optimal Brain Damage</a> paper <span class="citation" data-cites="lecun1989optimal">(<a href="references.html#ref-lecun1989optimal" role="doc-biblioref">LeCun, Denker, and Solla 1989</a>)</span>. This was later popularized in the context of deep learning by <span class="citation" data-cites="han2016deep">Han, Mao, and Dally (<a href="references.html#ref-han2016deep" role="doc-biblioref">2016</a>)</span>. In pruning, certain weights or even entire neurons are removed from the network, based on specific criteria. This can significantly reduce the model size. There are various strategies, like weight pruning, neuron pruning, and structured pruning. We will explore these in more detail in <a href="optimizations.html#sec-pruning"><span>Section&nbsp;10.3</span></a>.</p>
+<div class="no-row-height column-margin column-container"><div id="ref-lecun1989optimal" class="csl-entry" role="listitem">
+LeCun, Yann, John Denker, and Sara Solla. 1989. <span>“Optimal Brain Damage.”</span> <em>Advances in Neural Information Processing Systems</em> 2.
+</div><div id="ref-han2016deep" class="csl-entry" role="listitem">
+Han, Song, Huizi Mao, and William J. Dally. 2016. <span>“Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding.”</span> <a href="https://arxiv.org/abs/1510.00149">https://arxiv.org/abs/1510.00149</a>.
+</div></div><p><strong>Quantization</strong>: Quantization is the process of constraining an input from a large set to output in a smaller set, primarily in deep learning, this means reducing the number of bits that represent the weights and biases of the model. For example, using 16-bit or 8-bit representations instead of 32-bit can reduce model size and speed up computations, with a minor trade-off in accuracy. We will explore these in more detail in <a href="optimizations.html#sec-quant"><span>Section&nbsp;10.2</span></a>.</p>
+<p><strong>Knowledge Distillation</strong>: Knowledge distillation involves training a smaller model (student) to replicate the behavior of a larger model (teacher). The idea is to transfer the knowledge from the cumbersome model to the lightweight one, so the smaller model attains performance close to its larger counterpart but with significantly fewer parameters. We will explore knowledge distillation in more detail in the <a href="optimizations.html#sec-kd"><span>Section&nbsp;10.5</span></a>.</p>
 </section>
 <section id="efficient-inference-hardware" class="level2 page-columns page-full" data-number="9.5">
 <h2 data-number="9.5" class="anchored" data-anchor-id="efficient-inference-hardware"><span class="header-section-number">9.5</span> Efficient Inference Hardware</h2>
@@ -479,7 +489,7 @@ <h2 data-number="9.5" class="anchored" data-anchor-id="efficient-inference-hardw
 Jouppi, Norman P, Cliff Young, Nishant Patil, David Patterson, Gaurav Agrawal, Raminder Bajwa, Sarah Bates, et al. 2017. <span>“In-Datacenter Performance Analysis of a Tensor Processing Unit.”</span> In <em>Proceedings of the 44th Annual International Symposium on Computer Architecture</em>, 1–12.
 </div></div><p><a href="https://cloud.google.com/edge-tpu">Edge TPUs</a> are a smaller, power-efficient version of Google’s TPUs, tailored for edge devices. They provide fast on-device ML inferencing for TensorFlow Lite models. Edge TPUs allow for low-latency, high-efficiency inference on edge devices like smartphones, IoT devices, and embedded systems. This means AI capabilities can be deployed in real-time applications without needing to communicate with a central server, thus saving bandwidth and reducing latency.</p>
 <p><strong>NN Accelerators</strong>: Fixed function neural network accelerators are hardware accelerators designed explicitly for neural network computations. These can be standalone chips or part of a larger system-on-chip (SoC) solution. By optimizing the hardware for the specific operations that neural networks require, such as matrix multiplications and convolutions, NN accelerators can achieve faster inference times and lower power consumption compared to general-purpose CPUs and GPUs. They are especially beneficial in TinyML devices with power or thermal constraints, such as smartwatches, micro-drones, or robotics.</p>
-<p>But these are all but the most common place examples, there are a number of other types of hardware that are emerging that have the potential to offer signficiant advantages for inference. These include but are not limited to neuromorphic hardware, photonic computing, and so forth. In <a href="hw_acceleration.html"><span>Chapter&nbsp;11</span></a> we will explore these in greater detail.</p>
+<p>But these are all but the most common place examples, there are a number of other types of hardware that are emerging that have the potential to offer signficiant advantages for inference. These include but are not limited to neuromorphic hardware, photonic computing, and so forth. In <span class="quarto-unresolved-ref">?sec-ai_hw</span> we will explore these in greater detail.</p>
 <p>Efficient hardware for inference not only speeds up the process but also saves energy, extends battery life, and can operate in real-time conditions. As AI continues to be integrated into a myriad of applications – from smart cameras to voice assistants – the role of optimized hardware will only become more prominent. By leveraging these specialized hardware components, developers and engineers can bring the power of AI to devices and situations that were previously unthinkable.</p>
 </section>
 <section id="efficient-numerics" class="level2" data-number="9.6">
diff --git a/embedded_ml.html b/embedded_ml.html
index 98cfb19c8..1919e7464 100644
--- a/embedded_ml.html
+++ b/embedded_ml.html
@@ -8,7 +8,7 @@
 
 <meta name="keywords" content="open-source, embedded systems, machine learning, tinyML">
 
-<title>Machine Learning Systems for TinyML - 4&nbsp; Embedded AI</title>
+<title>MACHINE LEARNING SYSTEMS for TinyML - 4&nbsp; Embedded AI</title>
 <style>
 code{white-space: pre-wrap;}
 span.smallcaps{font-variant: small-caps;}
@@ -92,20 +92,20 @@
   <nav id="quarto-sidebar" class="sidebar collapse collapse-horizontal sidebar-navigation floating overflow-auto">
     <div class="pt-lg-2 mt-2 text-left sidebar-header">
     <div class="sidebar-title mb-0 py-0">
-      <a href="./">Machine Learning Systems for TinyML</a> 
+      <a href="./">MACHINE LEARNING SYSTEMS for TinyML</a> 
         <div class="sidebar-tools-main tools-wide">
     <a href="https://github.com/harvard-edge/cs249r_book" rel="" title="Source Code" class="quarto-navigation-tool px-1" aria-label="Source Code"><i class="bi bi-github"></i></a>
     <div class="dropdown">
       <a href="" title="Download" id="quarto-navigation-tool-dropdown-0" class="quarto-navigation-tool dropdown-toggle px-1" data-bs-toggle="dropdown" aria-expanded="false" aria-label="Download"><i class="bi bi-download"></i></a>
       <ul class="dropdown-menu" aria-labelledby="quarto-navigation-tool-dropdown-0">
           <li>
-            <a class="dropdown-item sidebar-tools-main-item" href="./Machine-Learning-Systems-for-TinyML.pdf">
+            <a class="dropdown-item sidebar-tools-main-item" href="./MACHINE-LEARNING-SYSTEMS-for-TinyML.pdf">
               <i class="bi bi-bi-file-pdf pe-1"></i>
             Download PDF
             </a>
           </li>
           <li>
-            <a class="dropdown-item sidebar-tools-main-item" href="./Machine-Learning-Systems-for-TinyML.epub">
+            <a class="dropdown-item sidebar-tools-main-item" href="./MACHINE-LEARNING-SYSTEMS-for-TinyML.epub">
               <i class="bi bi-bi-journal pe-1"></i>
             Download ePub
             </a>
@@ -421,6 +421,12 @@ <h1 class="title"><span class="chapter-number">4</span>&nbsp; <span class="chapt
     
   </div>
   
+<div>
+  <div class="abstract">
+    <div class="abstract-title">Abstract</div>
+    Machine Learning Systems for TinyML offers comprehensive guidance on deploying machine learning on embedded devices. As edge computing and the Internet of Things proliferate, this textbook provides professionals and students the expertise to implement performant AI on resource-constrained hardware. A unique aspect of this book elucidates the entire machine learning workflow, from data engineering through training, optimization, acceleration, and production deployment. Key topics covered include deep learning and classical ML algorithms for embedded systems, efficient neural network architectures, hardware-aware training techniques, model compression, benchmarking for tinyML, and on-device learning. Additional chapters highlight cutting-edge advances like on-device data generation and crucial considerations around reliability, privacy, security, and responsible AI. With its rigorous approach spanning theory and practice across diverse tinyML application domains like smart homes, wearables, and industrial IoT, the book enables readers to develop specialized knowledge. Using concrete use cases and hands-on examples, readers will learn to apply machine learning to transform embedded and IoT systems. Overall, this indispensable guide provides a research-based foundation for leveraging machine learning in embedded systems.
+  </div>
+</div>
 
 </header>
 
diff --git a/embedded_sys.html b/embedded_sys.html
index 53e6130d2..2676019ff 100644
--- a/embedded_sys.html
+++ b/embedded_sys.html
@@ -8,7 +8,7 @@
 
 <meta name="keywords" content="open-source, embedded systems, machine learning, tinyML">
 
-<title>Machine Learning Systems for TinyML - 2&nbsp; Embedded Systems</title>
+<title>MACHINE LEARNING SYSTEMS for TinyML - 2&nbsp; Embedded Systems</title>
 <style>
 code{white-space: pre-wrap;}
 span.smallcaps{font-variant: small-caps;}
@@ -145,20 +145,20 @@
   <nav id="quarto-sidebar" class="sidebar collapse collapse-horizontal sidebar-navigation floating overflow-auto">
     <div class="pt-lg-2 mt-2 text-left sidebar-header">
     <div class="sidebar-title mb-0 py-0">
-      <a href="./">Machine Learning Systems for TinyML</a> 
+      <a href="./">MACHINE LEARNING SYSTEMS for TinyML</a> 
         <div class="sidebar-tools-main tools-wide">
     <a href="https://github.com/harvard-edge/cs249r_book" rel="" title="Source Code" class="quarto-navigation-tool px-1" aria-label="Source Code"><i class="bi bi-github"></i></a>
     <div class="dropdown">
       <a href="" title="Download" id="quarto-navigation-tool-dropdown-0" class="quarto-navigation-tool dropdown-toggle px-1" data-bs-toggle="dropdown" aria-expanded="false" aria-label="Download"><i class="bi bi-download"></i></a>
       <ul class="dropdown-menu" aria-labelledby="quarto-navigation-tool-dropdown-0">
           <li>
-            <a class="dropdown-item sidebar-tools-main-item" href="./Machine-Learning-Systems-for-TinyML.pdf">
+            <a class="dropdown-item sidebar-tools-main-item" href="./MACHINE-LEARNING-SYSTEMS-for-TinyML.pdf">
               <i class="bi bi-bi-file-pdf pe-1"></i>
             Download PDF
             </a>
           </li>
           <li>
-            <a class="dropdown-item sidebar-tools-main-item" href="./Machine-Learning-Systems-for-TinyML.epub">
+            <a class="dropdown-item sidebar-tools-main-item" href="./MACHINE-LEARNING-SYSTEMS-for-TinyML.epub">
               <i class="bi bi-bi-journal pe-1"></i>
             Download ePub
             </a>
@@ -491,6 +491,12 @@ <h1 class="title"><span class="chapter-number">2</span>&nbsp; <span class="chapt
     
   </div>
   
+<div>
+  <div class="abstract">
+    <div class="abstract-title">Abstract</div>
+    Machine Learning Systems for TinyML offers comprehensive guidance on deploying machine learning on embedded devices. As edge computing and the Internet of Things proliferate, this textbook provides professionals and students the expertise to implement performant AI on resource-constrained hardware. A unique aspect of this book elucidates the entire machine learning workflow, from data engineering through training, optimization, acceleration, and production deployment. Key topics covered include deep learning and classical ML algorithms for embedded systems, efficient neural network architectures, hardware-aware training techniques, model compression, benchmarking for tinyML, and on-device learning. Additional chapters highlight cutting-edge advances like on-device data generation and crucial considerations around reliability, privacy, security, and responsible AI. With its rigorous approach spanning theory and practice across diverse tinyML application domains like smart homes, wearables, and industrial IoT, the book enables readers to develop specialized knowledge. Using concrete use cases and hands-on examples, readers will learn to apply machine learning to transform embedded and IoT systems. Overall, this indispensable guide provides a research-based foundation for leveraging machine learning in embedded systems.
+  </div>
+</div>
 
 </header>
 
diff --git a/frameworks.html b/frameworks.html
index 2369d71df..fa829af2c 100644
--- a/frameworks.html
+++ b/frameworks.html
@@ -8,7 +8,7 @@
 
 <meta name="keywords" content="open-source, embedded systems, machine learning, tinyML">
 
-<title>Machine Learning Systems for TinyML - 7&nbsp; AI Frameworks</title>
+<title>MACHINE LEARNING SYSTEMS for TinyML - 7&nbsp; AI Frameworks</title>
 <style>
 code{white-space: pre-wrap;}
 span.smallcaps{font-variant: small-caps;}
@@ -92,20 +92,20 @@
   <nav id="quarto-sidebar" class="sidebar collapse collapse-horizontal sidebar-navigation floating overflow-auto">
     <div class="pt-lg-2 mt-2 text-left sidebar-header">
     <div class="sidebar-title mb-0 py-0">
-      <a href="./">Machine Learning Systems for TinyML</a> 
+      <a href="./">MACHINE LEARNING SYSTEMS for TinyML</a> 
         <div class="sidebar-tools-main tools-wide">
     <a href="https://github.com/harvard-edge/cs249r_book" rel="" title="Source Code" class="quarto-navigation-tool px-1" aria-label="Source Code"><i class="bi bi-github"></i></a>
     <div class="dropdown">
       <a href="" title="Download" id="quarto-navigation-tool-dropdown-0" class="quarto-navigation-tool dropdown-toggle px-1" data-bs-toggle="dropdown" aria-expanded="false" aria-label="Download"><i class="bi bi-download"></i></a>
       <ul class="dropdown-menu" aria-labelledby="quarto-navigation-tool-dropdown-0">
           <li>
-            <a class="dropdown-item sidebar-tools-main-item" href="./Machine-Learning-Systems-for-TinyML.pdf">
+            <a class="dropdown-item sidebar-tools-main-item" href="./MACHINE-LEARNING-SYSTEMS-for-TinyML.pdf">
               <i class="bi bi-bi-file-pdf pe-1"></i>
             Download PDF
             </a>
           </li>
           <li>
-            <a class="dropdown-item sidebar-tools-main-item" href="./Machine-Learning-Systems-for-TinyML.epub">
+            <a class="dropdown-item sidebar-tools-main-item" href="./MACHINE-LEARNING-SYSTEMS-for-TinyML.epub">
               <i class="bi bi-bi-journal pe-1"></i>
             Download ePub
             </a>
@@ -405,6 +405,12 @@ <h1 class="title"><span class="chapter-number">7</span>&nbsp; <span class="chapt
     
   </div>
   
+<div>
+  <div class="abstract">
+    <div class="abstract-title">Abstract</div>
+    Machine Learning Systems for TinyML offers comprehensive guidance on deploying machine learning on embedded devices. As edge computing and the Internet of Things proliferate, this textbook provides professionals and students the expertise to implement performant AI on resource-constrained hardware. A unique aspect of this book elucidates the entire machine learning workflow, from data engineering through training, optimization, acceleration, and production deployment. Key topics covered include deep learning and classical ML algorithms for embedded systems, efficient neural network architectures, hardware-aware training techniques, model compression, benchmarking for tinyML, and on-device learning. Additional chapters highlight cutting-edge advances like on-device data generation and crucial considerations around reliability, privacy, security, and responsible AI. With its rigorous approach spanning theory and practice across diverse tinyML application domains like smart homes, wearables, and industrial IoT, the book enables readers to develop specialized knowledge. Using concrete use cases and hands-on examples, readers will learn to apply machine learning to transform embedded and IoT systems. Overall, this indispensable guide provides a research-based foundation for leveraging machine learning in embedded systems.
+  </div>
+</div>
 
 </header>
 
diff --git a/front.html b/front.html
index 3f5011a3e..9c683e41c 100644
--- a/front.html
+++ b/front.html
@@ -8,7 +8,7 @@
 
 <meta name="keywords" content="open-source, embedded systems, machine learning, tinyML">
 
-<title>Machine Learning Systems for TinyML - FRONT MATTER</title>
+<title>MACHINE LEARNING SYSTEMS for TinyML - FRONT MATTER</title>
 <style>
 code{white-space: pre-wrap;}
 span.smallcaps{font-variant: small-caps;}
@@ -91,20 +91,20 @@
   <nav id="quarto-sidebar" class="sidebar collapse collapse-horizontal sidebar-navigation floating overflow-auto">
     <div class="pt-lg-2 mt-2 text-left sidebar-header">
     <div class="sidebar-title mb-0 py-0">
-      <a href="./">Machine Learning Systems for TinyML</a> 
+      <a href="./">MACHINE LEARNING SYSTEMS for TinyML</a> 
         <div class="sidebar-tools-main tools-wide">
     <a href="https://github.com/harvard-edge/cs249r_book" rel="" title="Source Code" class="quarto-navigation-tool px-1" aria-label="Source Code"><i class="bi bi-github"></i></a>
     <div class="dropdown">
       <a href="" title="Download" id="quarto-navigation-tool-dropdown-0" class="quarto-navigation-tool dropdown-toggle px-1" data-bs-toggle="dropdown" aria-expanded="false" aria-label="Download"><i class="bi bi-download"></i></a>
       <ul class="dropdown-menu" aria-labelledby="quarto-navigation-tool-dropdown-0">
           <li>
-            <a class="dropdown-item sidebar-tools-main-item" href="./Machine-Learning-Systems-for-TinyML.pdf">
+            <a class="dropdown-item sidebar-tools-main-item" href="./MACHINE-LEARNING-SYSTEMS-for-TinyML.pdf">
               <i class="bi bi-bi-file-pdf pe-1"></i>
             Download PDF
             </a>
           </li>
           <li>
-            <a class="dropdown-item sidebar-tools-main-item" href="./Machine-Learning-Systems-for-TinyML.epub">
+            <a class="dropdown-item sidebar-tools-main-item" href="./MACHINE-LEARNING-SYSTEMS-for-TinyML.epub">
               <i class="bi bi-bi-journal pe-1"></i>
             Download ePub
             </a>
@@ -382,6 +382,12 @@ <h1 class="title">FRONT MATTER</h1>
     
   </div>
   
+<div>
+  <div class="abstract">
+    <div class="abstract-title">Abstract</div>
+    Machine Learning Systems for TinyML offers comprehensive guidance on deploying machine learning on embedded devices. As edge computing and the Internet of Things proliferate, this textbook provides professionals and students the expertise to implement performant AI on resource-constrained hardware. A unique aspect of this book elucidates the entire machine learning workflow, from data engineering through training, optimization, acceleration, and production deployment. Key topics covered include deep learning and classical ML algorithms for embedded systems, efficient neural network architectures, hardware-aware training techniques, model compression, benchmarking for tinyML, and on-device learning. Additional chapters highlight cutting-edge advances like on-device data generation and crucial considerations around reliability, privacy, security, and responsible AI. With its rigorous approach spanning theory and practice across diverse tinyML application domains like smart homes, wearables, and industrial IoT, the book enables readers to develop specialized knowledge. Using concrete use cases and hands-on examples, readers will learn to apply machine learning to transform embedded and IoT systems. Overall, this indispensable guide provides a research-based foundation for leveraging machine learning in embedded systems.
+  </div>
+</div>
 
 </header>
 
diff --git a/generative_ai.html b/generative_ai.html
index b2c8a6600..fad4c7375 100644
--- a/generative_ai.html
+++ b/generative_ai.html
@@ -8,7 +8,7 @@
 
 <meta name="keywords" content="open-source, embedded systems, machine learning, tinyML">
 
-<title>Machine Learning Systems for TinyML - 17&nbsp; Generative AI</title>
+<title>MACHINE LEARNING SYSTEMS for TinyML - 17&nbsp; Generative AI</title>
 <style>
 code{white-space: pre-wrap;}
 span.smallcaps{font-variant: small-caps;}
@@ -92,20 +92,20 @@
   <nav id="quarto-sidebar" class="sidebar collapse collapse-horizontal sidebar-navigation floating overflow-auto">
     <div class="pt-lg-2 mt-2 text-left sidebar-header">
     <div class="sidebar-title mb-0 py-0">
-      <a href="./">Machine Learning Systems for TinyML</a> 
+      <a href="./">MACHINE LEARNING SYSTEMS for TinyML</a> 
         <div class="sidebar-tools-main tools-wide">
     <a href="https://github.com/harvard-edge/cs249r_book" rel="" title="Source Code" class="quarto-navigation-tool px-1" aria-label="Source Code"><i class="bi bi-github"></i></a>
     <div class="dropdown">
       <a href="" title="Download" id="quarto-navigation-tool-dropdown-0" class="quarto-navigation-tool dropdown-toggle px-1" data-bs-toggle="dropdown" aria-expanded="false" aria-label="Download"><i class="bi bi-download"></i></a>
       <ul class="dropdown-menu" aria-labelledby="quarto-navigation-tool-dropdown-0">
           <li>
-            <a class="dropdown-item sidebar-tools-main-item" href="./Machine-Learning-Systems-for-TinyML.pdf">
+            <a class="dropdown-item sidebar-tools-main-item" href="./MACHINE-LEARNING-SYSTEMS-for-TinyML.pdf">
               <i class="bi bi-bi-file-pdf pe-1"></i>
             Download PDF
             </a>
           </li>
           <li>
-            <a class="dropdown-item sidebar-tools-main-item" href="./Machine-Learning-Systems-for-TinyML.epub">
+            <a class="dropdown-item sidebar-tools-main-item" href="./MACHINE-LEARNING-SYSTEMS-for-TinyML.epub">
               <i class="bi bi-bi-journal pe-1"></i>
             Download ePub
             </a>
@@ -398,6 +398,12 @@ <h1 class="title"><span class="chapter-number">17</span>&nbsp; <span class="chap
     
   </div>
   
+<div>
+  <div class="abstract">
+    <div class="abstract-title">Abstract</div>
+    Machine Learning Systems for TinyML offers comprehensive guidance on deploying machine learning on embedded devices. As edge computing and the Internet of Things proliferate, this textbook provides professionals and students the expertise to implement performant AI on resource-constrained hardware. A unique aspect of this book elucidates the entire machine learning workflow, from data engineering through training, optimization, acceleration, and production deployment. Key topics covered include deep learning and classical ML algorithms for embedded systems, efficient neural network architectures, hardware-aware training techniques, model compression, benchmarking for tinyML, and on-device learning. Additional chapters highlight cutting-edge advances like on-device data generation and crucial considerations around reliability, privacy, security, and responsible AI. With its rigorous approach spanning theory and practice across diverse tinyML application domains like smart homes, wearables, and industrial IoT, the book enables readers to develop specialized knowledge. Using concrete use cases and hands-on examples, readers will learn to apply machine learning to transform embedded and IoT systems. Overall, this indispensable guide provides a research-based foundation for leveraging machine learning in embedded systems.
+  </div>
+</div>
 
 </header>
 
diff --git a/hw_acceleration.html b/hw_acceleration.html
index d464006ff..addb8aca3 100644
--- a/hw_acceleration.html
+++ b/hw_acceleration.html
@@ -8,7 +8,7 @@
 
 <meta name="keywords" content="open-source, embedded systems, machine learning, tinyML">
 
-<title>Machine Learning Systems for TinyML - 11&nbsp; AI Acceleration</title>
+<title>MACHINE LEARNING SYSTEMS for TinyML - 11&nbsp; AI Acceleration</title>
 <style>
 code{white-space: pre-wrap;}
 span.smallcaps{font-variant: small-caps;}
@@ -92,20 +92,20 @@
   <nav id="quarto-sidebar" class="sidebar collapse collapse-horizontal sidebar-navigation floating overflow-auto">
     <div class="pt-lg-2 mt-2 text-left sidebar-header">
     <div class="sidebar-title mb-0 py-0">
-      <a href="./">Machine Learning Systems for TinyML</a> 
+      <a href="./">MACHINE LEARNING SYSTEMS for TinyML</a> 
         <div class="sidebar-tools-main tools-wide">
     <a href="https://github.com/harvard-edge/cs249r_book" rel="" title="Source Code" class="quarto-navigation-tool px-1" aria-label="Source Code"><i class="bi bi-github"></i></a>
     <div class="dropdown">
       <a href="" title="Download" id="quarto-navigation-tool-dropdown-0" class="quarto-navigation-tool dropdown-toggle px-1" data-bs-toggle="dropdown" aria-expanded="false" aria-label="Download"><i class="bi bi-download"></i></a>
       <ul class="dropdown-menu" aria-labelledby="quarto-navigation-tool-dropdown-0">
           <li>
-            <a class="dropdown-item sidebar-tools-main-item" href="./Machine-Learning-Systems-for-TinyML.pdf">
+            <a class="dropdown-item sidebar-tools-main-item" href="./MACHINE-LEARNING-SYSTEMS-for-TinyML.pdf">
               <i class="bi bi-bi-file-pdf pe-1"></i>
             Download PDF
             </a>
           </li>
           <li>
-            <a class="dropdown-item sidebar-tools-main-item" href="./Machine-Learning-Systems-for-TinyML.epub">
+            <a class="dropdown-item sidebar-tools-main-item" href="./MACHINE-LEARNING-SYSTEMS-for-TinyML.epub">
               <i class="bi bi-bi-journal pe-1"></i>
             Download ePub
             </a>
@@ -386,7 +386,7 @@ <h2 id="toc-title">Table of contents</h2>
 
 <header id="title-block-header" class="quarto-title-block default">
 <div class="quarto-title">
-<h1 class="title"><span id="sec-ai_hw" class="quarto-section-identifier"><span class="chapter-number">11</span>&nbsp; <span class="chapter-title">AI Acceleration</span></span></h1>
+<h1 class="title"><span class="chapter-number">11</span>&nbsp; <span class="chapter-title">AI Acceleration</span></h1>
 </div>
 
 
@@ -398,6 +398,12 @@ <h1 class="title"><span id="sec-ai_hw" class="quarto-section-identifier"><span c
     
   </div>
   
+<div>
+  <div class="abstract">
+    <div class="abstract-title">Abstract</div>
+    Machine Learning Systems for TinyML offers comprehensive guidance on deploying machine learning on embedded devices. As edge computing and the Internet of Things proliferate, this textbook provides professionals and students the expertise to implement performant AI on resource-constrained hardware. A unique aspect of this book elucidates the entire machine learning workflow, from data engineering through training, optimization, acceleration, and production deployment. Key topics covered include deep learning and classical ML algorithms for embedded systems, efficient neural network architectures, hardware-aware training techniques, model compression, benchmarking for tinyML, and on-device learning. Additional chapters highlight cutting-edge advances like on-device data generation and crucial considerations around reliability, privacy, security, and responsible AI. With its rigorous approach spanning theory and practice across diverse tinyML application domains like smart homes, wearables, and industrial IoT, the book enables readers to develop specialized knowledge. Using concrete use cases and hands-on examples, readers will learn to apply machine learning to transform embedded and IoT systems. Overall, this indispensable guide provides a research-based foundation for leveraging machine learning in embedded systems.
+  </div>
+</div>
 
 </header>
 
diff --git a/index.html b/index.html
index 7336b9d3a..508e49c21 100644
--- a/index.html
+++ b/index.html
@@ -8,7 +8,7 @@
 
 <meta name="keywords" content="open-source, embedded systems, machine learning, tinyML">
 
-<title>Machine Learning Systems for TinyML</title>
+<title>MACHINE LEARNING SYSTEMS for TinyML</title>
 <style>
 code{white-space: pre-wrap;}
 span.smallcaps{font-variant: small-caps;}
@@ -92,20 +92,20 @@
   <nav id="quarto-sidebar" class="sidebar collapse collapse-horizontal sidebar-navigation floating overflow-auto">
     <div class="pt-lg-2 mt-2 text-left sidebar-header">
     <div class="sidebar-title mb-0 py-0">
-      <a href="./">Machine Learning Systems for TinyML</a> 
+      <a href="./">MACHINE LEARNING SYSTEMS for TinyML</a> 
         <div class="sidebar-tools-main tools-wide">
     <a href="https://github.com/harvard-edge/cs249r_book" rel="" title="Source Code" class="quarto-navigation-tool px-1" aria-label="Source Code"><i class="bi bi-github"></i></a>
     <div class="dropdown">
       <a href="" title="Download" id="quarto-navigation-tool-dropdown-0" class="quarto-navigation-tool dropdown-toggle px-1" data-bs-toggle="dropdown" aria-expanded="false" aria-label="Download"><i class="bi bi-download"></i></a>
       <ul class="dropdown-menu" aria-labelledby="quarto-navigation-tool-dropdown-0">
           <li>
-            <a class="dropdown-item sidebar-tools-main-item" href="./Machine-Learning-Systems-for-TinyML.pdf">
+            <a class="dropdown-item sidebar-tools-main-item" href="./MACHINE-LEARNING-SYSTEMS-for-TinyML.pdf">
               <i class="bi bi-bi-file-pdf pe-1"></i>
             Download PDF
             </a>
           </li>
           <li>
-            <a class="dropdown-item sidebar-tools-main-item" href="./Machine-Learning-Systems-for-TinyML.epub">
+            <a class="dropdown-item sidebar-tools-main-item" href="./MACHINE-LEARNING-SYSTEMS-for-TinyML.epub">
               <i class="bi bi-bi-journal pe-1"></i>
             Download ePub
             </a>
@@ -383,7 +383,7 @@ <h2 id="toc-title">Table of contents</h2>
 
 <header id="title-block-header" class="quarto-title-block default">
 <div class="quarto-title">
-<h1 class="title">Machine Learning Systems for TinyML</h1>
+<h1 class="title">MACHINE LEARNING SYSTEMS for TinyML</h1>
 </div>
 
 
@@ -395,12 +395,18 @@ <h1 class="title">Machine Learning Systems for TinyML</h1>
     
   </div>
   
+<div>
+  <div class="abstract">
+    <div class="abstract-title">Abstract</div>
+    Machine Learning Systems for TinyML offers comprehensive guidance on deploying machine learning on embedded devices. As edge computing and the Internet of Things proliferate, this textbook provides professionals and students the expertise to implement performant AI on resource-constrained hardware. A unique aspect of this book elucidates the entire machine learning workflow, from data engineering through training, optimization, acceleration, and production deployment. Key topics covered include deep learning and classical ML algorithms for embedded systems, efficient neural network architectures, hardware-aware training techniques, model compression, benchmarking for tinyML, and on-device learning. Additional chapters highlight cutting-edge advances like on-device data generation and crucial considerations around reliability, privacy, security, and responsible AI. With its rigorous approach spanning theory and practice across diverse tinyML application domains like smart homes, wearables, and industrial IoT, the book enables readers to develop specialized knowledge. Using concrete use cases and hands-on examples, readers will learn to apply machine learning to transform embedded and IoT systems. Overall, this indispensable guide provides a research-based foundation for leveraging machine learning in embedded systems.
+  </div>
+</div>
 
 </header>
 
 
 <section id="preface" class="level1 unnumbered">
-<h1 class="unnumbered">Preface</h1><p><img src="cover.png" title="Machine Learning Systems for TinyML" class="quarto-cover-image img-fluid"></p>
+<h1 class="unnumbered">Preface</h1><p><img src="cover.png" title="MACHINE LEARNING SYSTEMS for TinyML" class="quarto-cover-image img-fluid"></p>
 <p>Welcome to “Machine Learning Systems for TinyML” This book is your gateway to the fast-paced world of artificial intelligence within embedded systems. It as an extension of the foundational course, tinyML from CS249r at Harvard University.</p>
 <p>Our aim? To make this book a collaborative effort that brings together insights from students, professionals, and the broader community. We want to create a one-stop guide that dives deep into the nuts and bolts of embedded AI and its many uses.</p>
 <blockquote class="blockquote">
diff --git a/introduction.html b/introduction.html
index 06c1ecc69..f189a816b 100644
--- a/introduction.html
+++ b/introduction.html
@@ -8,7 +8,7 @@
 
 <meta name="keywords" content="open-source, embedded systems, machine learning, tinyML">
 
-<title>Machine Learning Systems for TinyML - 1&nbsp; Introduction</title>
+<title>MACHINE LEARNING SYSTEMS for TinyML - 1&nbsp; Introduction</title>
 <style>
 code{white-space: pre-wrap;}
 span.smallcaps{font-variant: small-caps;}
@@ -92,20 +92,20 @@
   <nav id="quarto-sidebar" class="sidebar collapse collapse-horizontal sidebar-navigation floating overflow-auto">
     <div class="pt-lg-2 mt-2 text-left sidebar-header">
     <div class="sidebar-title mb-0 py-0">
-      <a href="./">Machine Learning Systems for TinyML</a> 
+      <a href="./">MACHINE LEARNING SYSTEMS for TinyML</a> 
         <div class="sidebar-tools-main tools-wide">
     <a href="https://github.com/harvard-edge/cs249r_book" rel="" title="Source Code" class="quarto-navigation-tool px-1" aria-label="Source Code"><i class="bi bi-github"></i></a>
     <div class="dropdown">
       <a href="" title="Download" id="quarto-navigation-tool-dropdown-0" class="quarto-navigation-tool dropdown-toggle px-1" data-bs-toggle="dropdown" aria-expanded="false" aria-label="Download"><i class="bi bi-download"></i></a>
       <ul class="dropdown-menu" aria-labelledby="quarto-navigation-tool-dropdown-0">
           <li>
-            <a class="dropdown-item sidebar-tools-main-item" href="./Machine-Learning-Systems-for-TinyML.pdf">
+            <a class="dropdown-item sidebar-tools-main-item" href="./MACHINE-LEARNING-SYSTEMS-for-TinyML.pdf">
               <i class="bi bi-bi-file-pdf pe-1"></i>
             Download PDF
             </a>
           </li>
           <li>
-            <a class="dropdown-item sidebar-tools-main-item" href="./Machine-Learning-Systems-for-TinyML.epub">
+            <a class="dropdown-item sidebar-tools-main-item" href="./MACHINE-LEARNING-SYSTEMS-for-TinyML.epub">
               <i class="bi bi-bi-journal pe-1"></i>
             Download ePub
             </a>
@@ -394,6 +394,12 @@ <h1 class="title"><span class="chapter-number">1</span>&nbsp; <span class="chapt
     
   </div>
   
+<div>
+  <div class="abstract">
+    <div class="abstract-title">Abstract</div>
+    Machine Learning Systems for TinyML offers comprehensive guidance on deploying machine learning on embedded devices. As edge computing and the Internet of Things proliferate, this textbook provides professionals and students the expertise to implement performant AI on resource-constrained hardware. A unique aspect of this book elucidates the entire machine learning workflow, from data engineering through training, optimization, acceleration, and production deployment. Key topics covered include deep learning and classical ML algorithms for embedded systems, efficient neural network architectures, hardware-aware training techniques, model compression, benchmarking for tinyML, and on-device learning. Additional chapters highlight cutting-edge advances like on-device data generation and crucial considerations around reliability, privacy, security, and responsible AI. With its rigorous approach spanning theory and practice across diverse tinyML application domains like smart homes, wearables, and industrial IoT, the book enables readers to develop specialized knowledge. Using concrete use cases and hands-on examples, readers will learn to apply machine learning to transform embedded and IoT systems. Overall, this indispensable guide provides a research-based foundation for leveraging machine learning in embedded systems.
+  </div>
+</div>
 
 </header>
 
diff --git a/learning_resources.html b/learning_resources.html
index 04fe8983c..b17935a22 100644
--- a/learning_resources.html
+++ b/learning_resources.html
@@ -8,7 +8,7 @@
 
 <meta name="keywords" content="open-source, embedded systems, machine learning, tinyML">
 
-<title>Machine Learning Systems for TinyML - Appendix D: Resources</title>
+<title>MACHINE LEARNING SYSTEMS for TinyML - Appendix D: Resources</title>
 <style>
 code{white-space: pre-wrap;}
 span.smallcaps{font-variant: small-caps;}
@@ -92,20 +92,20 @@
   <nav id="quarto-sidebar" class="sidebar collapse collapse-horizontal sidebar-navigation floating overflow-auto">
     <div class="pt-lg-2 mt-2 text-left sidebar-header">
     <div class="sidebar-title mb-0 py-0">
-      <a href="./">Machine Learning Systems for TinyML</a> 
+      <a href="./">MACHINE LEARNING SYSTEMS for TinyML</a> 
         <div class="sidebar-tools-main tools-wide">
     <a href="https://github.com/harvard-edge/cs249r_book" rel="" title="Source Code" class="quarto-navigation-tool px-1" aria-label="Source Code"><i class="bi bi-github"></i></a>
     <div class="dropdown">
       <a href="" title="Download" id="quarto-navigation-tool-dropdown-0" class="quarto-navigation-tool dropdown-toggle px-1" data-bs-toggle="dropdown" aria-expanded="false" aria-label="Download"><i class="bi bi-download"></i></a>
       <ul class="dropdown-menu" aria-labelledby="quarto-navigation-tool-dropdown-0">
           <li>
-            <a class="dropdown-item sidebar-tools-main-item" href="./Machine-Learning-Systems-for-TinyML.pdf">
+            <a class="dropdown-item sidebar-tools-main-item" href="./MACHINE-LEARNING-SYSTEMS-for-TinyML.pdf">
               <i class="bi bi-bi-file-pdf pe-1"></i>
             Download PDF
             </a>
           </li>
           <li>
-            <a class="dropdown-item sidebar-tools-main-item" href="./Machine-Learning-Systems-for-TinyML.epub">
+            <a class="dropdown-item sidebar-tools-main-item" href="./MACHINE-LEARNING-SYSTEMS-for-TinyML.epub">
               <i class="bi bi-bi-journal pe-1"></i>
             Download ePub
             </a>
@@ -392,6 +392,12 @@ <h1 class="title">Appendix D: Resources</h1>
     
   </div>
   
+<div>
+  <div class="abstract">
+    <div class="abstract-title">Abstract</div>
+    Machine Learning Systems for TinyML offers comprehensive guidance on deploying machine learning on embedded devices. As edge computing and the Internet of Things proliferate, this textbook provides professionals and students the expertise to implement performant AI on resource-constrained hardware. A unique aspect of this book elucidates the entire machine learning workflow, from data engineering through training, optimization, acceleration, and production deployment. Key topics covered include deep learning and classical ML algorithms for embedded systems, efficient neural network architectures, hardware-aware training techniques, model compression, benchmarking for tinyML, and on-device learning. Additional chapters highlight cutting-edge advances like on-device data generation and crucial considerations around reliability, privacy, security, and responsible AI. With its rigorous approach spanning theory and practice across diverse tinyML application domains like smart homes, wearables, and industrial IoT, the book enables readers to develop specialized knowledge. Using concrete use cases and hands-on examples, readers will learn to apply machine learning to transform embedded and IoT systems. Overall, this indispensable guide provides a research-based foundation for leveraging machine learning in embedded systems.
+  </div>
+</div>
 
 </header>
 
diff --git a/ondevice_learning.html b/ondevice_learning.html
index 51a57d547..18d54042b 100644
--- a/ondevice_learning.html
+++ b/ondevice_learning.html
@@ -8,7 +8,7 @@
 
 <meta name="keywords" content="open-source, embedded systems, machine learning, tinyML">
 
-<title>Machine Learning Systems for TinyML - 13&nbsp; On-Device Learning</title>
+<title>MACHINE LEARNING SYSTEMS for TinyML - 13&nbsp; On-Device Learning</title>
 <style>
 code{white-space: pre-wrap;}
 span.smallcaps{font-variant: small-caps;}
@@ -92,20 +92,20 @@
   <nav id="quarto-sidebar" class="sidebar collapse collapse-horizontal sidebar-navigation floating overflow-auto">
     <div class="pt-lg-2 mt-2 text-left sidebar-header">
     <div class="sidebar-title mb-0 py-0">
-      <a href="./">Machine Learning Systems for TinyML</a> 
+      <a href="./">MACHINE LEARNING SYSTEMS for TinyML</a> 
         <div class="sidebar-tools-main tools-wide">
     <a href="https://github.com/harvard-edge/cs249r_book" rel="" title="Source Code" class="quarto-navigation-tool px-1" aria-label="Source Code"><i class="bi bi-github"></i></a>
     <div class="dropdown">
       <a href="" title="Download" id="quarto-navigation-tool-dropdown-0" class="quarto-navigation-tool dropdown-toggle px-1" data-bs-toggle="dropdown" aria-expanded="false" aria-label="Download"><i class="bi bi-download"></i></a>
       <ul class="dropdown-menu" aria-labelledby="quarto-navigation-tool-dropdown-0">
           <li>
-            <a class="dropdown-item sidebar-tools-main-item" href="./Machine-Learning-Systems-for-TinyML.pdf">
+            <a class="dropdown-item sidebar-tools-main-item" href="./MACHINE-LEARNING-SYSTEMS-for-TinyML.pdf">
               <i class="bi bi-bi-file-pdf pe-1"></i>
             Download PDF
             </a>
           </li>
           <li>
-            <a class="dropdown-item sidebar-tools-main-item" href="./Machine-Learning-Systems-for-TinyML.epub">
+            <a class="dropdown-item sidebar-tools-main-item" href="./MACHINE-LEARNING-SYSTEMS-for-TinyML.epub">
               <i class="bi bi-bi-journal pe-1"></i>
             Download ePub
             </a>
@@ -396,6 +396,12 @@ <h1 class="title"><span class="chapter-number">13</span>&nbsp; <span class="chap
     
   </div>
   
+<div>
+  <div class="abstract">
+    <div class="abstract-title">Abstract</div>
+    Machine Learning Systems for TinyML offers comprehensive guidance on deploying machine learning on embedded devices. As edge computing and the Internet of Things proliferate, this textbook provides professionals and students the expertise to implement performant AI on resource-constrained hardware. A unique aspect of this book elucidates the entire machine learning workflow, from data engineering through training, optimization, acceleration, and production deployment. Key topics covered include deep learning and classical ML algorithms for embedded systems, efficient neural network architectures, hardware-aware training techniques, model compression, benchmarking for tinyML, and on-device learning. Additional chapters highlight cutting-edge advances like on-device data generation and crucial considerations around reliability, privacy, security, and responsible AI. With its rigorous approach spanning theory and practice across diverse tinyML application domains like smart homes, wearables, and industrial IoT, the book enables readers to develop specialized knowledge. Using concrete use cases and hands-on examples, readers will learn to apply machine learning to transform embedded and IoT systems. Overall, this indispensable guide provides a research-based foundation for leveraging machine learning in embedded systems.
+  </div>
+</div>
 
 </header>
 
diff --git a/ops.html b/ops.html
index 8c11b19fb..1a521fda1 100644
--- a/ops.html
+++ b/ops.html
@@ -8,7 +8,7 @@
 
 <meta name="keywords" content="open-source, embedded systems, machine learning, tinyML">
 
-<title>Machine Learning Systems for TinyML - 14&nbsp; Embedded AIOps</title>
+<title>MACHINE LEARNING SYSTEMS for TinyML - 14&nbsp; Embedded AIOps</title>
 <style>
 code{white-space: pre-wrap;}
 span.smallcaps{font-variant: small-caps;}
@@ -92,20 +92,20 @@
   <nav id="quarto-sidebar" class="sidebar collapse collapse-horizontal sidebar-navigation floating overflow-auto">
     <div class="pt-lg-2 mt-2 text-left sidebar-header">
     <div class="sidebar-title mb-0 py-0">
-      <a href="./">Machine Learning Systems for TinyML</a> 
+      <a href="./">MACHINE LEARNING SYSTEMS for TinyML</a> 
         <div class="sidebar-tools-main tools-wide">
     <a href="https://github.com/harvard-edge/cs249r_book" rel="" title="Source Code" class="quarto-navigation-tool px-1" aria-label="Source Code"><i class="bi bi-github"></i></a>
     <div class="dropdown">
       <a href="" title="Download" id="quarto-navigation-tool-dropdown-0" class="quarto-navigation-tool dropdown-toggle px-1" data-bs-toggle="dropdown" aria-expanded="false" aria-label="Download"><i class="bi bi-download"></i></a>
       <ul class="dropdown-menu" aria-labelledby="quarto-navigation-tool-dropdown-0">
           <li>
-            <a class="dropdown-item sidebar-tools-main-item" href="./Machine-Learning-Systems-for-TinyML.pdf">
+            <a class="dropdown-item sidebar-tools-main-item" href="./MACHINE-LEARNING-SYSTEMS-for-TinyML.pdf">
               <i class="bi bi-bi-file-pdf pe-1"></i>
             Download PDF
             </a>
           </li>
           <li>
-            <a class="dropdown-item sidebar-tools-main-item" href="./Machine-Learning-Systems-for-TinyML.epub">
+            <a class="dropdown-item sidebar-tools-main-item" href="./MACHINE-LEARNING-SYSTEMS-for-TinyML.epub">
               <i class="bi bi-bi-journal pe-1"></i>
             Download ePub
             </a>
@@ -396,6 +396,12 @@ <h1 class="title"><span class="chapter-number">14</span>&nbsp; <span class="chap
     
   </div>
   
+<div>
+  <div class="abstract">
+    <div class="abstract-title">Abstract</div>
+    Machine Learning Systems for TinyML offers comprehensive guidance on deploying machine learning on embedded devices. As edge computing and the Internet of Things proliferate, this textbook provides professionals and students the expertise to implement performant AI on resource-constrained hardware. A unique aspect of this book elucidates the entire machine learning workflow, from data engineering through training, optimization, acceleration, and production deployment. Key topics covered include deep learning and classical ML algorithms for embedded systems, efficient neural network architectures, hardware-aware training techniques, model compression, benchmarking for tinyML, and on-device learning. Additional chapters highlight cutting-edge advances like on-device data generation and crucial considerations around reliability, privacy, security, and responsible AI. With its rigorous approach spanning theory and practice across diverse tinyML application domains like smart homes, wearables, and industrial IoT, the book enables readers to develop specialized knowledge. Using concrete use cases and hands-on examples, readers will learn to apply machine learning to transform embedded and IoT systems. Overall, this indispensable guide provides a research-based foundation for leveraging machine learning in embedded systems.
+  </div>
+</div>
 
 </header>
 
diff --git a/optimizations.html b/optimizations.html
index 40d6be9af..c9fac8f03 100644
--- a/optimizations.html
+++ b/optimizations.html
@@ -8,7 +8,7 @@
 
 <meta name="keywords" content="open-source, embedded systems, machine learning, tinyML">
 
-<title>Machine Learning Systems for TinyML - 10&nbsp; Model Optimizations</title>
+<title>MACHINE LEARNING SYSTEMS for TinyML - 10&nbsp; Model Optimizations</title>
 <style>
 code{white-space: pre-wrap;}
 span.smallcaps{font-variant: small-caps;}
@@ -92,20 +92,20 @@
   <nav id="quarto-sidebar" class="sidebar collapse collapse-horizontal sidebar-navigation floating overflow-auto">
     <div class="pt-lg-2 mt-2 text-left sidebar-header">
     <div class="sidebar-title mb-0 py-0">
-      <a href="./">Machine Learning Systems for TinyML</a> 
+      <a href="./">MACHINE LEARNING SYSTEMS for TinyML</a> 
         <div class="sidebar-tools-main tools-wide">
     <a href="https://github.com/harvard-edge/cs249r_book" rel="" title="Source Code" class="quarto-navigation-tool px-1" aria-label="Source Code"><i class="bi bi-github"></i></a>
     <div class="dropdown">
       <a href="" title="Download" id="quarto-navigation-tool-dropdown-0" class="quarto-navigation-tool dropdown-toggle px-1" data-bs-toggle="dropdown" aria-expanded="false" aria-label="Download"><i class="bi bi-download"></i></a>
       <ul class="dropdown-menu" aria-labelledby="quarto-navigation-tool-dropdown-0">
           <li>
-            <a class="dropdown-item sidebar-tools-main-item" href="./Machine-Learning-Systems-for-TinyML.pdf">
+            <a class="dropdown-item sidebar-tools-main-item" href="./MACHINE-LEARNING-SYSTEMS-for-TinyML.pdf">
               <i class="bi bi-bi-file-pdf pe-1"></i>
             Download PDF
             </a>
           </li>
           <li>
-            <a class="dropdown-item sidebar-tools-main-item" href="./Machine-Learning-Systems-for-TinyML.epub">
+            <a class="dropdown-item sidebar-tools-main-item" href="./MACHINE-LEARNING-SYSTEMS-for-TinyML.epub">
               <i class="bi bi-bi-journal pe-1"></i>
             Download ePub
             </a>
@@ -369,10 +369,10 @@ <h2 id="toc-title">Table of contents</h2>
    
   <ul>
   <li><a href="#introduction" id="toc-introduction" class="nav-link active" data-scroll-target="#introduction"><span class="header-section-number">10.1</span> Introduction</a></li>
-  <li><a href="#quantization" id="toc-quantization" class="nav-link" data-scroll-target="#quantization"><span class="header-section-number">10.2</span> Quantization</a></li>
-  <li><a href="#pruning" id="toc-pruning" class="nav-link" data-scroll-target="#pruning"><span class="header-section-number">10.3</span> Pruning</a></li>
+  <li><a href="#sec-quant" id="toc-sec-quant" class="nav-link" data-scroll-target="#sec-quant"><span class="header-section-number">10.2</span> Quantization</a></li>
+  <li><a href="#sec-pruning" id="toc-sec-pruning" class="nav-link" data-scroll-target="#sec-pruning"><span class="header-section-number">10.3</span> Pruning</a></li>
   <li><a href="#kernel-and-graph-optimization" id="toc-kernel-and-graph-optimization" class="nav-link" data-scroll-target="#kernel-and-graph-optimization"><span class="header-section-number">10.4</span> Kernel and Graph Optimization</a></li>
-  <li><a href="#model-compression" id="toc-model-compression" class="nav-link" data-scroll-target="#model-compression"><span class="header-section-number">10.5</span> Model Compression</a></li>
+  <li><a href="#sec-kd" id="toc-sec-kd" class="nav-link" data-scroll-target="#sec-kd"><span class="header-section-number">10.5</span> Model Compression</a></li>
   <li><a href="#efficient-model-architectures" id="toc-efficient-model-architectures" class="nav-link" data-scroll-target="#efficient-model-architectures"><span class="header-section-number">10.6</span> Efficient Model Architectures</a></li>
   <li><a href="#hardware-aware-training" id="toc-hardware-aware-training" class="nav-link" data-scroll-target="#hardware-aware-training"><span class="header-section-number">10.7</span> Hardware-Aware Training</a></li>
   <li><a href="#dynamic-model-loading" id="toc-dynamic-model-loading" class="nav-link" data-scroll-target="#dynamic-model-loading"><span class="header-section-number">10.8</span> Dynamic Model Loading</a></li>
@@ -397,6 +397,12 @@ <h1 class="title"><span class="chapter-number">10</span>&nbsp; <span class="chap
     
   </div>
   
+<div>
+  <div class="abstract">
+    <div class="abstract-title">Abstract</div>
+    Machine Learning Systems for TinyML offers comprehensive guidance on deploying machine learning on embedded devices. As edge computing and the Internet of Things proliferate, this textbook provides professionals and students the expertise to implement performant AI on resource-constrained hardware. A unique aspect of this book elucidates the entire machine learning workflow, from data engineering through training, optimization, acceleration, and production deployment. Key topics covered include deep learning and classical ML algorithms for embedded systems, efficient neural network architectures, hardware-aware training techniques, model compression, benchmarking for tinyML, and on-device learning. Additional chapters highlight cutting-edge advances like on-device data generation and crucial considerations around reliability, privacy, security, and responsible AI. With its rigorous approach spanning theory and practice across diverse tinyML application domains like smart homes, wearables, and industrial IoT, the book enables readers to develop specialized knowledge. Using concrete use cases and hands-on examples, readers will learn to apply machine learning to transform embedded and IoT systems. Overall, this indispensable guide provides a research-based foundation for leveraging machine learning in embedded systems.
+  </div>
+</div>
 
 </header>
 
@@ -409,8 +415,8 @@ <h2 data-number="10.1" class="anchored" data-anchor-id="introduction"><span clas
 <li>Optimization approaches: pruning, quantization, efficient architectures, etc.</li>
 </ul>
 </section>
-<section id="quantization" class="level2" data-number="10.2">
-<h2 data-number="10.2" class="anchored" data-anchor-id="quantization"><span class="header-section-number">10.2</span> Quantization</h2>
+<section id="sec-quant" class="level2" data-number="10.2">
+<h2 data-number="10.2" class="anchored" data-anchor-id="sec-quant"><span class="header-section-number">10.2</span> Quantization</h2>
 <p>Explanation: Quantization is a critical technique in model optimization, helping to reduce the computational and memory demands of AI models without substantially sacrificing their performance. Through various methods and schemas, it facilitates the deployment of deep learning models on embedded devices with limited resources.</p>
 <ul>
 <li>Motivation for model quantization</li>
@@ -421,8 +427,8 @@ <h2 data-number="10.2" class="anchored" data-anchor-id="quantization"><span clas
 <li>Quantization in practice: deployment frameworks</li>
 </ul>
 </section>
-<section id="pruning" class="level2" data-number="10.3">
-<h2 data-number="10.3" class="anchored" data-anchor-id="pruning"><span class="header-section-number">10.3</span> Pruning</h2>
+<section id="sec-pruning" class="level2" data-number="10.3">
+<h2 data-number="10.3" class="anchored" data-anchor-id="sec-pruning"><span class="header-section-number">10.3</span> Pruning</h2>
 <p>Explanation: Pruning is an optimization approach that focuses on eliminating unnecessary connections and weights in a neural network, without affecting its ability to make accurate predictions. It is essential in enhancing the efficiency of AI models by reducing their size and computational demands, hence making them faster and more suitable for deployment on devices with limited resources.</p>
 <ul>
 <li>Overview of pruning techniques</li>
@@ -444,8 +450,8 @@ <h2 data-number="10.4" class="anchored" data-anchor-id="kernel-and-graph-optimiz
 <li>Graph Rewriting</li>
 </ul>
 </section>
-<section id="model-compression" class="level2" data-number="10.5">
-<h2 data-number="10.5" class="anchored" data-anchor-id="model-compression"><span class="header-section-number">10.5</span> Model Compression</h2>
+<section id="sec-kd" class="level2" data-number="10.5">
+<h2 data-number="10.5" class="anchored" data-anchor-id="sec-kd"><span class="header-section-number">10.5</span> Model Compression</h2>
 <p>Explanation: Model compression is crucial in reducing the computational complexity of deep learning models while preserving their predictive performance. This section delves into various techniques that facilitate the compression of models, making them lighter and more manageable for deployment on resource-constrained devices, thereby fostering quicker and more efficient AI implementations.</p>
 <ul>
 <li>Knowledge distillation</li>
diff --git a/privacy_security.html b/privacy_security.html
index ee6a2c377..c31f4c140 100644
--- a/privacy_security.html
+++ b/privacy_security.html
@@ -8,7 +8,7 @@
 
 <meta name="keywords" content="open-source, embedded systems, machine learning, tinyML">
 
-<title>Machine Learning Systems for TinyML - 15&nbsp; Privacy and Security</title>
+<title>MACHINE LEARNING SYSTEMS for TinyML - 15&nbsp; Privacy and Security</title>
 <style>
 code{white-space: pre-wrap;}
 span.smallcaps{font-variant: small-caps;}
@@ -92,20 +92,20 @@
   <nav id="quarto-sidebar" class="sidebar collapse collapse-horizontal sidebar-navigation floating overflow-auto">
     <div class="pt-lg-2 mt-2 text-left sidebar-header">
     <div class="sidebar-title mb-0 py-0">
-      <a href="./">Machine Learning Systems for TinyML</a> 
+      <a href="./">MACHINE LEARNING SYSTEMS for TinyML</a> 
         <div class="sidebar-tools-main tools-wide">
     <a href="https://github.com/harvard-edge/cs249r_book" rel="" title="Source Code" class="quarto-navigation-tool px-1" aria-label="Source Code"><i class="bi bi-github"></i></a>
     <div class="dropdown">
       <a href="" title="Download" id="quarto-navigation-tool-dropdown-0" class="quarto-navigation-tool dropdown-toggle px-1" data-bs-toggle="dropdown" aria-expanded="false" aria-label="Download"><i class="bi bi-download"></i></a>
       <ul class="dropdown-menu" aria-labelledby="quarto-navigation-tool-dropdown-0">
           <li>
-            <a class="dropdown-item sidebar-tools-main-item" href="./Machine-Learning-Systems-for-TinyML.pdf">
+            <a class="dropdown-item sidebar-tools-main-item" href="./MACHINE-LEARNING-SYSTEMS-for-TinyML.pdf">
               <i class="bi bi-bi-file-pdf pe-1"></i>
             Download PDF
             </a>
           </li>
           <li>
-            <a class="dropdown-item sidebar-tools-main-item" href="./Machine-Learning-Systems-for-TinyML.epub">
+            <a class="dropdown-item sidebar-tools-main-item" href="./MACHINE-LEARNING-SYSTEMS-for-TinyML.epub">
               <i class="bi bi-bi-journal pe-1"></i>
             Download ePub
             </a>
@@ -397,6 +397,12 @@ <h1 class="title"><span class="chapter-number">15</span>&nbsp; <span class="chap
     
   </div>
   
+<div>
+  <div class="abstract">
+    <div class="abstract-title">Abstract</div>
+    Machine Learning Systems for TinyML offers comprehensive guidance on deploying machine learning on embedded devices. As edge computing and the Internet of Things proliferate, this textbook provides professionals and students the expertise to implement performant AI on resource-constrained hardware. A unique aspect of this book elucidates the entire machine learning workflow, from data engineering through training, optimization, acceleration, and production deployment. Key topics covered include deep learning and classical ML algorithms for embedded systems, efficient neural network architectures, hardware-aware training techniques, model compression, benchmarking for tinyML, and on-device learning. Additional chapters highlight cutting-edge advances like on-device data generation and crucial considerations around reliability, privacy, security, and responsible AI. With its rigorous approach spanning theory and practice across diverse tinyML application domains like smart homes, wearables, and industrial IoT, the book enables readers to develop specialized knowledge. Using concrete use cases and hands-on examples, readers will learn to apply machine learning to transform embedded and IoT systems. Overall, this indispensable guide provides a research-based foundation for leveraging machine learning in embedded systems.
+  </div>
+</div>
 
 </header>
 
diff --git a/references.html b/references.html
index 6c4dae638..a25cf8164 100644
--- a/references.html
+++ b/references.html
@@ -8,7 +8,7 @@
 
 <meta name="keywords" content="open-source, embedded systems, machine learning, tinyML">
 
-<title>Machine Learning Systems for TinyML - References</title>
+<title>MACHINE LEARNING SYSTEMS for TinyML - References</title>
 <style>
 code{white-space: pre-wrap;}
 span.smallcaps{font-variant: small-caps;}
@@ -111,20 +111,20 @@
   <nav id="quarto-sidebar" class="sidebar collapse collapse-horizontal sidebar-navigation floating overflow-auto">
     <div class="pt-lg-2 mt-2 text-left sidebar-header">
     <div class="sidebar-title mb-0 py-0">
-      <a href="./">Machine Learning Systems for TinyML</a> 
+      <a href="./">MACHINE LEARNING SYSTEMS for TinyML</a> 
         <div class="sidebar-tools-main tools-wide">
     <a href="https://github.com/harvard-edge/cs249r_book" rel="" title="Source Code" class="quarto-navigation-tool px-1" aria-label="Source Code"><i class="bi bi-github"></i></a>
     <div class="dropdown">
       <a href="" title="Download" id="quarto-navigation-tool-dropdown-0" class="quarto-navigation-tool dropdown-toggle px-1" data-bs-toggle="dropdown" aria-expanded="false" aria-label="Download"><i class="bi bi-download"></i></a>
       <ul class="dropdown-menu" aria-labelledby="quarto-navigation-tool-dropdown-0">
           <li>
-            <a class="dropdown-item sidebar-tools-main-item" href="./Machine-Learning-Systems-for-TinyML.pdf">
+            <a class="dropdown-item sidebar-tools-main-item" href="./MACHINE-LEARNING-SYSTEMS-for-TinyML.pdf">
               <i class="bi bi-bi-file-pdf pe-1"></i>
             Download PDF
             </a>
           </li>
           <li>
-            <a class="dropdown-item sidebar-tools-main-item" href="./Machine-Learning-Systems-for-TinyML.epub">
+            <a class="dropdown-item sidebar-tools-main-item" href="./MACHINE-LEARNING-SYSTEMS-for-TinyML.epub">
               <i class="bi bi-bi-journal pe-1"></i>
             Download ePub
             </a>
@@ -402,6 +402,12 @@ <h1 class="title">References</h1>
     
   </div>
   
+<div>
+  <div class="abstract">
+    <div class="abstract-title">Abstract</div>
+    Machine Learning Systems for TinyML offers comprehensive guidance on deploying machine learning on embedded devices. As edge computing and the Internet of Things proliferate, this textbook provides professionals and students the expertise to implement performant AI on resource-constrained hardware. A unique aspect of this book elucidates the entire machine learning workflow, from data engineering through training, optimization, acceleration, and production deployment. Key topics covered include deep learning and classical ML algorithms for embedded systems, efficient neural network architectures, hardware-aware training techniques, model compression, benchmarking for tinyML, and on-device learning. Additional chapters highlight cutting-edge advances like on-device data generation and crucial considerations around reliability, privacy, security, and responsible AI. With its rigorous approach spanning theory and practice across diverse tinyML application domains like smart homes, wearables, and industrial IoT, the book enables readers to develop specialized knowledge. Using concrete use cases and hands-on examples, readers will learn to apply machine learning to transform embedded and IoT systems. Overall, this indispensable guide provides a research-based foundation for leveraging machine learning in embedded systems.
+  </div>
+</div>
 
 </header>
 
@@ -431,6 +437,11 @@ <h1 class="title">References</h1>
 <span>“Generative Adversarial Networks.”</span> <em>Communications of
 the ACM</em> 63 (11): 139–44.
 </div>
+<div id="ref-han2016deep" class="csl-entry" role="listitem">
+Han, Song, Huizi Mao, and William J. Dally. 2016. <span>“Deep
+Compression: Compressing Deep Neural Networks with Pruning, Trained
+Quantization and Huffman Coding.”</span> <a href="https://arxiv.org/abs/1510.00149">https://arxiv.org/abs/1510.00149</a>.
+</div>
 <div id="ref-he2016deep" class="csl-entry" role="listitem">
 He, Kaiming, Xiangyu Zhang, Shaoqing Ren, and Jian Sun. 2016.
 <span>“Deep Residual Learning for Image Recognition.”</span> In
@@ -462,6 +473,11 @@ <h1 class="title">References</h1>
 Networks.”</span> <em>Advances in Neural Information Processing
 Systems</em> 25.
 </div>
+<div id="ref-lecun1989optimal" class="csl-entry" role="listitem">
+LeCun, Yann, John Denker, and Sara Solla. 1989. <span>“Optimal Brain
+Damage.”</span> <em>Advances in Neural Information Processing
+Systems</em> 2.
+</div>
 <div id="ref-li2019edge" class="csl-entry" role="listitem">
 Li, En, Liekang Zeng, Zhi Zhou, and Xu Chen. 2019. <span>“Edge AI:
 On-Demand Accelerating Deep Neural Network Inference via Edge
diff --git a/responsible_ai.html b/responsible_ai.html
index 7580ab782..220588743 100644
--- a/responsible_ai.html
+++ b/responsible_ai.html
@@ -8,7 +8,7 @@
 
 <meta name="keywords" content="open-source, embedded systems, machine learning, tinyML">
 
-<title>Machine Learning Systems for TinyML - 16&nbsp; Responsible AI</title>
+<title>MACHINE LEARNING SYSTEMS for TinyML - 16&nbsp; Responsible AI</title>
 <style>
 code{white-space: pre-wrap;}
 span.smallcaps{font-variant: small-caps;}
@@ -92,20 +92,20 @@
   <nav id="quarto-sidebar" class="sidebar collapse collapse-horizontal sidebar-navigation floating overflow-auto">
     <div class="pt-lg-2 mt-2 text-left sidebar-header">
     <div class="sidebar-title mb-0 py-0">
-      <a href="./">Machine Learning Systems for TinyML</a> 
+      <a href="./">MACHINE LEARNING SYSTEMS for TinyML</a> 
         <div class="sidebar-tools-main tools-wide">
     <a href="https://github.com/harvard-edge/cs249r_book" rel="" title="Source Code" class="quarto-navigation-tool px-1" aria-label="Source Code"><i class="bi bi-github"></i></a>
     <div class="dropdown">
       <a href="" title="Download" id="quarto-navigation-tool-dropdown-0" class="quarto-navigation-tool dropdown-toggle px-1" data-bs-toggle="dropdown" aria-expanded="false" aria-label="Download"><i class="bi bi-download"></i></a>
       <ul class="dropdown-menu" aria-labelledby="quarto-navigation-tool-dropdown-0">
           <li>
-            <a class="dropdown-item sidebar-tools-main-item" href="./Machine-Learning-Systems-for-TinyML.pdf">
+            <a class="dropdown-item sidebar-tools-main-item" href="./MACHINE-LEARNING-SYSTEMS-for-TinyML.pdf">
               <i class="bi bi-bi-file-pdf pe-1"></i>
             Download PDF
             </a>
           </li>
           <li>
-            <a class="dropdown-item sidebar-tools-main-item" href="./Machine-Learning-Systems-for-TinyML.epub">
+            <a class="dropdown-item sidebar-tools-main-item" href="./MACHINE-LEARNING-SYSTEMS-for-TinyML.epub">
               <i class="bi bi-bi-journal pe-1"></i>
             Download ePub
             </a>
@@ -397,6 +397,12 @@ <h1 class="title"><span class="chapter-number">16</span>&nbsp; <span class="chap
     
   </div>
   
+<div>
+  <div class="abstract">
+    <div class="abstract-title">Abstract</div>
+    Machine Learning Systems for TinyML offers comprehensive guidance on deploying machine learning on embedded devices. As edge computing and the Internet of Things proliferate, this textbook provides professionals and students the expertise to implement performant AI on resource-constrained hardware. A unique aspect of this book elucidates the entire machine learning workflow, from data engineering through training, optimization, acceleration, and production deployment. Key topics covered include deep learning and classical ML algorithms for embedded systems, efficient neural network architectures, hardware-aware training techniques, model compression, benchmarking for tinyML, and on-device learning. Additional chapters highlight cutting-edge advances like on-device data generation and crucial considerations around reliability, privacy, security, and responsible AI. With its rigorous approach spanning theory and practice across diverse tinyML application domains like smart homes, wearables, and industrial IoT, the book enables readers to develop specialized knowledge. Using concrete use cases and hands-on examples, readers will learn to apply machine learning to transform embedded and IoT systems. Overall, this indispensable guide provides a research-based foundation for leveraging machine learning in embedded systems.
+  </div>
+</div>
 
 </header>
 
diff --git a/search.json b/search.json
index 46b93a666..d06c86329 100644
--- a/search.json
+++ b/search.json
@@ -2,7 +2,7 @@
   {
     "objectID": "index.html",
     "href": "index.html",
-    "title": "Machine Learning Systems for TinyML",
+    "title": "MACHINE LEARNING SYSTEMS for TinyML",
     "section": "",
     "text": "Preface\nWelcome to “Machine Learning Systems for TinyML” This book is your gateway to the fast-paced world of artificial intelligence within embedded systems. It as an extension of the foundational course, tinyML from CS249r at Harvard University.\nOur aim? To make this book a collaborative effort that brings together insights from students, professionals, and the broader community. We want to create a one-stop guide that dives deep into the nuts and bolts of embedded AI and its many uses.\n\n“If you want to go fast, go alone. If you want to go far, go together.” – African Proverb\n\nThis isn’t just a static textbook; it’s a living, breathing document. We’re making it open-source and continually updated to meet the ever-changing needs of this dynamic field. Expect a rich blend of expert knowledge that guides you through the complex interplay between cutting-edge algorithms and the foundational principles that make them work. We’re setting the stage for the next big leap in tech innovation.\n\n\nWhy We Wrote This Book\nWe’re in an age where technology is always evolving. Open collaboration and sharing knowledge are the building blocks of true innovation. That’s the spirit behind “Machine Learning Systems for TinyML.” We’re going beyond the traditional textbook model to create a living knowledge hub.\nThe book covers principles, algorithms, and real-world application case studies, aiming to give you a deep understanding that will help you navigate the ever-changing landscape of embedded AI. By keeping it open, we’re not just making learning accessible; we’re inviting new ideas and ongoing improvements. In short, we’re building a community where knowledge is free to grow and light the way forward in global embedded AI tech.\n\n\nWhat You’ll Need to Know\nDon’t worry, you don’t need to be a machine learning whiz to dive into this book. All you really need is a basic understanding of systems and a curiosity to explore how embedded hardware, AI, and software come together. This is where innovation happens, and a basic grasp of how systems work will be your compass.\nWe’re also focusing on the exciting overlaps between these fields, aiming to create a learning environment where traditional boundaries fade away, making room for a more holistic, integrated view of modern tech. Your interest in embedded AI and low-level software will guide you through a rich and rewarding learning experience.\n\n\nBook Conventions\nFor details on the conventions used in this book, check out the Conventions section.\n\n\nWant to Help Out?\nIf you’re interested in contributing, you can find the guidelines here.\n\n\nGet in Touch\nGot questions or feedback? Feel free to e-mail us.\n\n\nContributors\nA big thanks to everyone who’s helped make this book what it is! You can see the full list of contributors here."
   },
@@ -25,7 +25,7 @@
     "href": "contributors.html",
     "title": "Contributors",
     "section": "",
-    "text": "We extend our sincere thanks to the diverse group of individuals who have generously contributed their expertise, insights, and time to enhance both the content and codebase of this project. Below you will find a list of all contributors. If you would like to contribute to this project, please see our GitHub page.\n\n\n\n\n\n\n\n\nMatthew Stewart📖\n\n\nVijay Janapa Reddi📖\n\n\nShvetank Prakash📖\n\n\nIkechukwu Uchendu📖"
+    "text": "We extend our sincere thanks to the diverse group of individuals who have generously contributed their expertise, insights, and time to enhance both the content and codebase of this project. Below you will find a list of all contributors. If you would like to contribute to this project, please see our GitHub page.\n\n\n\n\n\n\n\n\nShvetank Prakash📖\n\n\nVijay Janapa Reddi📖\n\n\nMatthew Stewart📖\n\n\nIkechukwu Uchendu📖"
   },
   {
     "objectID": "copyright.html",
@@ -550,14 +550,14 @@
     "href": "efficient_ai.html#efficient-model-compression",
     "title": "9  Efficient AI",
     "section": "9.4 Efficient Model Compression",
-    "text": "9.4 Efficient Model Compression\nModel compression methods are very important for bringing deep learning models to devices with limited resources. These techniques reduce the size, energy consumption, and computational demands of models without a significant loss in accuracy. At a high level, the methods can briefly be binned into the following fundamental methods:\nPruning: This is akin to trimming the branches of a tree. In pruning, certain weights or even entire neurons are removed from the network, based on specific criteria. This can significantly reduce the model size. There are various strategies, like weight pruning, neuron pruning, and structured pruning.\nQuantization: Quantization is the process of constraining an input from a large set to output in a smaller set, primarily in deep learning, this means reducing the number of bits that represent the weights and biases of the model. For example, using 16-bit or 8-bit representations instead of 32-bit can reduce model size and speed up computations, with a minor trade-off in accuracy.\nKnowledge Distillation: Knowledge distillation involves training a smaller model (student) to replicate the behavior of a larger model (teacher). The idea is to transfer the knowledge from the cumbersome model to the lightweight one, so the smaller model attains performance close to its larger counterpart but with significantly fewer parameters."
+    "text": "9.4 Efficient Model Compression\nModel compression methods are very important for bringing deep learning models to devices with limited resources. These techniques reduce the size, energy consumption, and computational demands of models without a significant loss in accuracy. At a high level, the methods can briefly be binned into the following fundamental methods:\nPruning: This is akin to trimming the branches of a tree. This was first thought of in the Optimal Brain Damage paper (LeCun, Denker, and Solla 1989). This was later popularized in the context of deep learning by Han, Mao, and Dally (2016). In pruning, certain weights or even entire neurons are removed from the network, based on specific criteria. This can significantly reduce the model size. There are various strategies, like weight pruning, neuron pruning, and structured pruning. We will explore these in more detail in Section 10.3.\n\nLeCun, Yann, John Denker, and Sara Solla. 1989. “Optimal Brain Damage.” Advances in Neural Information Processing Systems 2.\n\nHan, Song, Huizi Mao, and William J. Dally. 2016. “Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding.” https://arxiv.org/abs/1510.00149.\nQuantization: Quantization is the process of constraining an input from a large set to output in a smaller set, primarily in deep learning, this means reducing the number of bits that represent the weights and biases of the model. For example, using 16-bit or 8-bit representations instead of 32-bit can reduce model size and speed up computations, with a minor trade-off in accuracy. We will explore these in more detail in Section 10.2.\nKnowledge Distillation: Knowledge distillation involves training a smaller model (student) to replicate the behavior of a larger model (teacher). The idea is to transfer the knowledge from the cumbersome model to the lightweight one, so the smaller model attains performance close to its larger counterpart but with significantly fewer parameters. We will explore knowledge distillation in more detail in the Section 10.5."
   },
   {
     "objectID": "efficient_ai.html#efficient-inference-hardware",
     "href": "efficient_ai.html#efficient-inference-hardware",
     "title": "9  Efficient AI",
     "section": "9.5 Efficient Inference Hardware",
-    "text": "9.5 Efficient Inference Hardware\nTraining an AI model is an intensive task that requires powerful hardware and can take hours to weeks, but inference needs to be as fast as possible, especially in real-time applications. This is where efficient inference hardware comes into play. By optimizing the hardware specifically for inference tasks, we can achieve rapid response times and power-efficient operation, especially crucial for edge devices and embedded systems.\nTPUs (Tensor Processing Units): TPUs are custom-built ASICs (Application-Specific Integrated Circuits) by Google to accelerate machine learning workloads (Jouppi et al. 2017). They are optimized for tensor operations, offering high throughput for low-precision arithmetic, and are designed specifically for neural network machine learning. TPUs deliver a significant acceleration in model training and inference as compared to general-purpose GPU/CPUs. This boost means faster model training and real-time or near-real-time inference capabilities, crucial for applications like voice search and augmented reality.\n\nJouppi, Norman P, Cliff Young, Nishant Patil, David Patterson, Gaurav Agrawal, Raminder Bajwa, Sarah Bates, et al. 2017. “In-Datacenter Performance Analysis of a Tensor Processing Unit.” In Proceedings of the 44th Annual International Symposium on Computer Architecture, 1–12.\nEdge TPUs are a smaller, power-efficient version of Google’s TPUs, tailored for edge devices. They provide fast on-device ML inferencing for TensorFlow Lite models. Edge TPUs allow for low-latency, high-efficiency inference on edge devices like smartphones, IoT devices, and embedded systems. This means AI capabilities can be deployed in real-time applications without needing to communicate with a central server, thus saving bandwidth and reducing latency.\nNN Accelerators: Fixed function neural network accelerators are hardware accelerators designed explicitly for neural network computations. These can be standalone chips or part of a larger system-on-chip (SoC) solution. By optimizing the hardware for the specific operations that neural networks require, such as matrix multiplications and convolutions, NN accelerators can achieve faster inference times and lower power consumption compared to general-purpose CPUs and GPUs. They are especially beneficial in TinyML devices with power or thermal constraints, such as smartwatches, micro-drones, or robotics.\nBut these are all but the most common place examples, there are a number of other types of hardware that are emerging that have the potential to offer signficiant advantages for inference. These include but are not limited to neuromorphic hardware, photonic computing, and so forth. In Chapter 11 we will explore these in greater detail.\nEfficient hardware for inference not only speeds up the process but also saves energy, extends battery life, and can operate in real-time conditions. As AI continues to be integrated into a myriad of applications – from smart cameras to voice assistants – the role of optimized hardware will only become more prominent. By leveraging these specialized hardware components, developers and engineers can bring the power of AI to devices and situations that were previously unthinkable."
+    "text": "9.5 Efficient Inference Hardware\nTraining an AI model is an intensive task that requires powerful hardware and can take hours to weeks, but inference needs to be as fast as possible, especially in real-time applications. This is where efficient inference hardware comes into play. By optimizing the hardware specifically for inference tasks, we can achieve rapid response times and power-efficient operation, especially crucial for edge devices and embedded systems.\nTPUs (Tensor Processing Units): TPUs are custom-built ASICs (Application-Specific Integrated Circuits) by Google to accelerate machine learning workloads (Jouppi et al. 2017). They are optimized for tensor operations, offering high throughput for low-precision arithmetic, and are designed specifically for neural network machine learning. TPUs deliver a significant acceleration in model training and inference as compared to general-purpose GPU/CPUs. This boost means faster model training and real-time or near-real-time inference capabilities, crucial for applications like voice search and augmented reality.\n\nJouppi, Norman P, Cliff Young, Nishant Patil, David Patterson, Gaurav Agrawal, Raminder Bajwa, Sarah Bates, et al. 2017. “In-Datacenter Performance Analysis of a Tensor Processing Unit.” In Proceedings of the 44th Annual International Symposium on Computer Architecture, 1–12.\nEdge TPUs are a smaller, power-efficient version of Google’s TPUs, tailored for edge devices. They provide fast on-device ML inferencing for TensorFlow Lite models. Edge TPUs allow for low-latency, high-efficiency inference on edge devices like smartphones, IoT devices, and embedded systems. This means AI capabilities can be deployed in real-time applications without needing to communicate with a central server, thus saving bandwidth and reducing latency.\nNN Accelerators: Fixed function neural network accelerators are hardware accelerators designed explicitly for neural network computations. These can be standalone chips or part of a larger system-on-chip (SoC) solution. By optimizing the hardware for the specific operations that neural networks require, such as matrix multiplications and convolutions, NN accelerators can achieve faster inference times and lower power consumption compared to general-purpose CPUs and GPUs. They are especially beneficial in TinyML devices with power or thermal constraints, such as smartwatches, micro-drones, or robotics.\nBut these are all but the most common place examples, there are a number of other types of hardware that are emerging that have the potential to offer signficiant advantages for inference. These include but are not limited to neuromorphic hardware, photonic computing, and so forth. In ?sec-ai_hw we will explore these in greater detail.\nEfficient hardware for inference not only speeds up the process but also saves energy, extends battery life, and can operate in real-time conditions. As AI continues to be integrated into a myriad of applications – from smart cameras to voice assistants – the role of optimized hardware will only become more prominent. By leveraging these specialized hardware components, developers and engineers can bring the power of AI to devices and situations that were previously unthinkable."
   },
   {
     "objectID": "efficient_ai.html#efficient-numerics",
@@ -588,15 +588,15 @@
     "text": "10.1 Introduction\nThis chapter stands as a critical overview of what is coming in the next few chapters that will offer readers an in-depth exploration of the multifaceted world of ML frameworks, highlighting their significance, functionalities, and the potential to revolutionize embedded systems development. As embedded devices continue to permeate various aspects of daily life, from healthcare to home automation, a comprehensive understanding of these frameworks not only serves as a bridge between concept and application but also as a catalyst in fostering innovations that are efficient, adaptable, and primed for the future.\n\nOverview of model optimization techniques for efficient AI\nMotivations: reduce model size, latency, power consumption, etc.\nOptimization approaches: pruning, quantization, efficient architectures, etc."
   },
   {
-    "objectID": "optimizations.html#quantization",
-    "href": "optimizations.html#quantization",
+    "objectID": "optimizations.html#sec-quant",
+    "href": "optimizations.html#sec-quant",
     "title": "10  Model Optimizations",
     "section": "10.2 Quantization",
     "text": "10.2 Quantization\nExplanation: Quantization is a critical technique in model optimization, helping to reduce the computational and memory demands of AI models without substantially sacrificing their performance. Through various methods and schemas, it facilitates the deployment of deep learning models on embedded devices with limited resources.\n\nMotivation for model quantization\nPost-training quantization\nQuantization-aware training\nHandling activations vs weights\nQuantization schemas: uniform, mixed, per-channel\nQuantization in practice: deployment frameworks"
   },
   {
-    "objectID": "optimizations.html#pruning",
-    "href": "optimizations.html#pruning",
+    "objectID": "optimizations.html#sec-pruning",
+    "href": "optimizations.html#sec-pruning",
     "title": "10  Model Optimizations",
     "section": "10.3 Pruning",
     "text": "10.3 Pruning\nExplanation: Pruning is an optimization approach that focuses on eliminating unnecessary connections and weights in a neural network, without affecting its ability to make accurate predictions. It is essential in enhancing the efficiency of AI models by reducing their size and computational demands, hence making them faster and more suitable for deployment on devices with limited resources.\n\nOverview of pruning techniques\nStructured vs unstructured pruning\nMagnitude-based pruning\nIterative pruning and re-training\nLottery ticket hypothesis\nPruning in practice: frameworks, results"
@@ -609,8 +609,8 @@
     "text": "10.4 Kernel and Graph Optimization\nExplanation: Kernel and graph optimization is a critical component in the process of tailoring AI models to the specific constraints of embedded systems, helping to ensure that these models can operate efficiently and effectively even in resource-constrained environments.\n\nConvolution Algorithms\nMM Kernels\nLayer Fusion\nNode Elimination\nGraph Rewriting"
   },
   {
-    "objectID": "optimizations.html#model-compression",
-    "href": "optimizations.html#model-compression",
+    "objectID": "optimizations.html#sec-kd",
+    "href": "optimizations.html#sec-kd",
     "title": "10  Model Optimizations",
     "section": "10.5 Model Compression",
     "text": "10.5 Model Compression\nExplanation: Model compression is crucial in reducing the computational complexity of deep learning models while preserving their predictive performance. This section delves into various techniques that facilitate the compression of models, making them lighter and more manageable for deployment on resource-constrained devices, thereby fostering quicker and more efficient AI implementations.\n\nKnowledge distillation\nTensor decomposition methods\nLow-rank matrix factorization\nLearned approximations of weight matrices"
@@ -1208,7 +1208,7 @@
     "href": "references.html",
     "title": "References",
     "section": "",
-    "text": "ARM.com. “The Future Is Being Built on Arm: Market Diversification\nContinues to Drive Strong Royalty and Licensing Growth as Ecosystem\nReaches Quarter of a Trillion Chips Milestone – Arm®.” https://www.arm.com/company/news/2023/02/arm-announces-q3-fy22-results.\n\n\nBank, Dor, Noam Koenigstein, and Raja Giryes. 2023.\n“Autoencoders.” Machine Learning for Data Science\nHandbook: Data Mining and Knowledge Discovery Handbook, 353–74.\n\n\nBarroso, Luiz André, Urs Hölzle, and Parthasarathy Ranganathan. 2019.\nThe Datacenter as a Computer: Designing Warehouse-Scale\nMachines. Springer Nature.\n\n\nGoodfellow, Ian, Jean Pouget-Abadie, Mehdi Mirza, Bing Xu, David\nWarde-Farley, Sherjil Ozair, Aaron Courville, and Yoshua Bengio. 2020.\n“Generative Adversarial Networks.” Communications of\nthe ACM 63 (11): 139–44.\n\n\nHe, Kaiming, Xiangyu Zhang, Shaoqing Ren, and Jian Sun. 2016.\n“Deep Residual Learning for Image Recognition.” In\nProceedings of the IEEE Conference on Computer Vision and Pattern\nRecognition, 770–78.\n\n\nHoward, Andrew G, Menglong Zhu, Bo Chen, Dmitry Kalenichenko, Weijun\nWang, Tobias Weyand, Marco Andreetto, and Hartwig Adam. 2017.\n“Mobilenets: Efficient Convolutional Neural Networks for Mobile\nVision Applications.” arXiv Preprint arXiv:1704.04861.\n\n\nIandola, Forrest N, Song Han, Matthew W Moskewicz, Khalid Ashraf,\nWilliam J Dally, and Kurt Keutzer. 2016. “SqueezeNet:\nAlexNet-Level Accuracy with 50x Fewer Parameters and&lt; 0.5 MB Model\nSize.” arXiv Preprint arXiv:1602.07360.\n\n\nJouppi, Norman P, Cliff Young, Nishant Patil, David Patterson, Gaurav\nAgrawal, Raminder Bajwa, Sarah Bates, et al. 2017. “In-Datacenter\nPerformance Analysis of a Tensor Processing Unit.” In\nProceedings of the 44th Annual International Symposium on Computer\nArchitecture, 1–12.\n\n\nKrizhevsky, Alex, Ilya Sutskever, and Geoffrey E Hinton. 2012.\n“Imagenet Classification with Deep Convolutional Neural\nNetworks.” Advances in Neural Information Processing\nSystems 25.\n\n\nLi, En, Liekang Zeng, Zhi Zhou, and Xu Chen. 2019. “Edge AI:\nOn-Demand Accelerating Deep Neural Network Inference via Edge\nComputing.” IEEE Transactions on Wireless Communications\n19 (1): 447–57.\n\n\nRosenblatt, Frank. 1957. The Perceptron, a Perceiving and\nRecognizing Automaton Project Para. Cornell Aeronautical\nLaboratory.\n\n\nRumelhart, David E, Geoffrey E Hinton, and Ronald J Williams. 1986.\n“Learning Representations by Back-Propagating Errors.”\nNature 323 (6088): 533–36.\n\n\nVaswani, Ashish, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion\nJones, Aidan N Gomez, Łukasz Kaiser, and Illia Polosukhin. 2017.\n“Attention Is All You Need.” Advances in Neural\nInformation Processing Systems 30.\n\n\nWarden, Pete, and Daniel Situnayake. 2019. Tinyml: Machine Learning\nwith Tensorflow Lite on Arduino and Ultra-Low-Power\nMicrocontrollers. O’Reilly Media."
+    "text": "ARM.com. “The Future Is Being Built on Arm: Market Diversification\nContinues to Drive Strong Royalty and Licensing Growth as Ecosystem\nReaches Quarter of a Trillion Chips Milestone – Arm®.” https://www.arm.com/company/news/2023/02/arm-announces-q3-fy22-results.\n\n\nBank, Dor, Noam Koenigstein, and Raja Giryes. 2023.\n“Autoencoders.” Machine Learning for Data Science\nHandbook: Data Mining and Knowledge Discovery Handbook, 353–74.\n\n\nBarroso, Luiz André, Urs Hölzle, and Parthasarathy Ranganathan. 2019.\nThe Datacenter as a Computer: Designing Warehouse-Scale\nMachines. Springer Nature.\n\n\nGoodfellow, Ian, Jean Pouget-Abadie, Mehdi Mirza, Bing Xu, David\nWarde-Farley, Sherjil Ozair, Aaron Courville, and Yoshua Bengio. 2020.\n“Generative Adversarial Networks.” Communications of\nthe ACM 63 (11): 139–44.\n\n\nHan, Song, Huizi Mao, and William J. Dally. 2016. “Deep\nCompression: Compressing Deep Neural Networks with Pruning, Trained\nQuantization and Huffman Coding.” https://arxiv.org/abs/1510.00149.\n\n\nHe, Kaiming, Xiangyu Zhang, Shaoqing Ren, and Jian Sun. 2016.\n“Deep Residual Learning for Image Recognition.” In\nProceedings of the IEEE Conference on Computer Vision and Pattern\nRecognition, 770–78.\n\n\nHoward, Andrew G, Menglong Zhu, Bo Chen, Dmitry Kalenichenko, Weijun\nWang, Tobias Weyand, Marco Andreetto, and Hartwig Adam. 2017.\n“Mobilenets: Efficient Convolutional Neural Networks for Mobile\nVision Applications.” arXiv Preprint arXiv:1704.04861.\n\n\nIandola, Forrest N, Song Han, Matthew W Moskewicz, Khalid Ashraf,\nWilliam J Dally, and Kurt Keutzer. 2016. “SqueezeNet:\nAlexNet-Level Accuracy with 50x Fewer Parameters and&lt; 0.5 MB Model\nSize.” arXiv Preprint arXiv:1602.07360.\n\n\nJouppi, Norman P, Cliff Young, Nishant Patil, David Patterson, Gaurav\nAgrawal, Raminder Bajwa, Sarah Bates, et al. 2017. “In-Datacenter\nPerformance Analysis of a Tensor Processing Unit.” In\nProceedings of the 44th Annual International Symposium on Computer\nArchitecture, 1–12.\n\n\nKrizhevsky, Alex, Ilya Sutskever, and Geoffrey E Hinton. 2012.\n“Imagenet Classification with Deep Convolutional Neural\nNetworks.” Advances in Neural Information Processing\nSystems 25.\n\n\nLeCun, Yann, John Denker, and Sara Solla. 1989. “Optimal Brain\nDamage.” Advances in Neural Information Processing\nSystems 2.\n\n\nLi, En, Liekang Zeng, Zhi Zhou, and Xu Chen. 2019. “Edge AI:\nOn-Demand Accelerating Deep Neural Network Inference via Edge\nComputing.” IEEE Transactions on Wireless Communications\n19 (1): 447–57.\n\n\nRosenblatt, Frank. 1957. The Perceptron, a Perceiving and\nRecognizing Automaton Project Para. Cornell Aeronautical\nLaboratory.\n\n\nRumelhart, David E, Geoffrey E Hinton, and Ronald J Williams. 1986.\n“Learning Representations by Back-Propagating Errors.”\nNature 323 (6088): 533–36.\n\n\nVaswani, Ashish, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion\nJones, Aidan N Gomez, Łukasz Kaiser, and Illia Polosukhin. 2017.\n“Attention Is All You Need.” Advances in Neural\nInformation Processing Systems 30.\n\n\nWarden, Pete, and Daniel Situnayake. 2019. Tinyml: Machine Learning\nwith Tensorflow Lite on Arduino and Ultra-Low-Power\nMicrocontrollers. O’Reilly Media."
   },
   {
     "objectID": "tools.html#hardware-kits",
diff --git a/sustainable_ai.html b/sustainable_ai.html
index ea5749f4f..22df3cd82 100644
--- a/sustainable_ai.html
+++ b/sustainable_ai.html
@@ -8,7 +8,7 @@
 
 <meta name="keywords" content="open-source, embedded systems, machine learning, tinyML">
 
-<title>Machine Learning Systems for TinyML - 19&nbsp; Sustainable AI</title>
+<title>MACHINE LEARNING SYSTEMS for TinyML - 19&nbsp; Sustainable AI</title>
 <style>
 code{white-space: pre-wrap;}
 span.smallcaps{font-variant: small-caps;}
@@ -92,20 +92,20 @@
   <nav id="quarto-sidebar" class="sidebar collapse collapse-horizontal sidebar-navigation floating overflow-auto">
     <div class="pt-lg-2 mt-2 text-left sidebar-header">
     <div class="sidebar-title mb-0 py-0">
-      <a href="./">Machine Learning Systems for TinyML</a> 
+      <a href="./">MACHINE LEARNING SYSTEMS for TinyML</a> 
         <div class="sidebar-tools-main tools-wide">
     <a href="https://github.com/harvard-edge/cs249r_book" rel="" title="Source Code" class="quarto-navigation-tool px-1" aria-label="Source Code"><i class="bi bi-github"></i></a>
     <div class="dropdown">
       <a href="" title="Download" id="quarto-navigation-tool-dropdown-0" class="quarto-navigation-tool dropdown-toggle px-1" data-bs-toggle="dropdown" aria-expanded="false" aria-label="Download"><i class="bi bi-download"></i></a>
       <ul class="dropdown-menu" aria-labelledby="quarto-navigation-tool-dropdown-0">
           <li>
-            <a class="dropdown-item sidebar-tools-main-item" href="./Machine-Learning-Systems-for-TinyML.pdf">
+            <a class="dropdown-item sidebar-tools-main-item" href="./MACHINE-LEARNING-SYSTEMS-for-TinyML.pdf">
               <i class="bi bi-bi-file-pdf pe-1"></i>
             Download PDF
             </a>
           </li>
           <li>
-            <a class="dropdown-item sidebar-tools-main-item" href="./Machine-Learning-Systems-for-TinyML.epub">
+            <a class="dropdown-item sidebar-tools-main-item" href="./MACHINE-LEARNING-SYSTEMS-for-TinyML.epub">
               <i class="bi bi-bi-journal pe-1"></i>
             Download ePub
             </a>
@@ -398,6 +398,12 @@ <h1 class="title"><span class="chapter-number">19</span>&nbsp; <span class="chap
     
   </div>
   
+<div>
+  <div class="abstract">
+    <div class="abstract-title">Abstract</div>
+    Machine Learning Systems for TinyML offers comprehensive guidance on deploying machine learning on embedded devices. As edge computing and the Internet of Things proliferate, this textbook provides professionals and students the expertise to implement performant AI on resource-constrained hardware. A unique aspect of this book elucidates the entire machine learning workflow, from data engineering through training, optimization, acceleration, and production deployment. Key topics covered include deep learning and classical ML algorithms for embedded systems, efficient neural network architectures, hardware-aware training techniques, model compression, benchmarking for tinyML, and on-device learning. Additional chapters highlight cutting-edge advances like on-device data generation and crucial considerations around reliability, privacy, security, and responsible AI. With its rigorous approach spanning theory and practice across diverse tinyML application domains like smart homes, wearables, and industrial IoT, the book enables readers to develop specialized knowledge. Using concrete use cases and hands-on examples, readers will learn to apply machine learning to transform embedded and IoT systems. Overall, this indispensable guide provides a research-based foundation for leveraging machine learning in embedded systems.
+  </div>
+</div>
 
 </header>
 
diff --git a/tools.html b/tools.html
index abbbb2314..95653d7f4 100644
--- a/tools.html
+++ b/tools.html
@@ -8,7 +8,7 @@
 
 <meta name="keywords" content="open-source, embedded systems, machine learning, tinyML">
 
-<title>Machine Learning Systems for TinyML - Appendix A: Tools</title>
+<title>MACHINE LEARNING SYSTEMS for TinyML - Appendix A: Tools</title>
 <style>
 code{white-space: pre-wrap;}
 span.smallcaps{font-variant: small-caps;}
@@ -92,20 +92,20 @@
   <nav id="quarto-sidebar" class="sidebar collapse collapse-horizontal sidebar-navigation floating overflow-auto">
     <div class="pt-lg-2 mt-2 text-left sidebar-header">
     <div class="sidebar-title mb-0 py-0">
-      <a href="./">Machine Learning Systems for TinyML</a> 
+      <a href="./">MACHINE LEARNING SYSTEMS for TinyML</a> 
         <div class="sidebar-tools-main tools-wide">
     <a href="https://github.com/harvard-edge/cs249r_book" rel="" title="Source Code" class="quarto-navigation-tool px-1" aria-label="Source Code"><i class="bi bi-github"></i></a>
     <div class="dropdown">
       <a href="" title="Download" id="quarto-navigation-tool-dropdown-0" class="quarto-navigation-tool dropdown-toggle px-1" data-bs-toggle="dropdown" aria-expanded="false" aria-label="Download"><i class="bi bi-download"></i></a>
       <ul class="dropdown-menu" aria-labelledby="quarto-navigation-tool-dropdown-0">
           <li>
-            <a class="dropdown-item sidebar-tools-main-item" href="./Machine-Learning-Systems-for-TinyML.pdf">
+            <a class="dropdown-item sidebar-tools-main-item" href="./MACHINE-LEARNING-SYSTEMS-for-TinyML.pdf">
               <i class="bi bi-bi-file-pdf pe-1"></i>
             Download PDF
             </a>
           </li>
           <li>
-            <a class="dropdown-item sidebar-tools-main-item" href="./Machine-Learning-Systems-for-TinyML.epub">
+            <a class="dropdown-item sidebar-tools-main-item" href="./MACHINE-LEARNING-SYSTEMS-for-TinyML.epub">
               <i class="bi bi-bi-journal pe-1"></i>
             Download ePub
             </a>
@@ -398,6 +398,12 @@ <h1 class="title">Appendix A: Tools</h1>
     
   </div>
   
+<div>
+  <div class="abstract">
+    <div class="abstract-title">Abstract</div>
+    Machine Learning Systems for TinyML offers comprehensive guidance on deploying machine learning on embedded devices. As edge computing and the Internet of Things proliferate, this textbook provides professionals and students the expertise to implement performant AI on resource-constrained hardware. A unique aspect of this book elucidates the entire machine learning workflow, from data engineering through training, optimization, acceleration, and production deployment. Key topics covered include deep learning and classical ML algorithms for embedded systems, efficient neural network architectures, hardware-aware training techniques, model compression, benchmarking for tinyML, and on-device learning. Additional chapters highlight cutting-edge advances like on-device data generation and crucial considerations around reliability, privacy, security, and responsible AI. With its rigorous approach spanning theory and practice across diverse tinyML application domains like smart homes, wearables, and industrial IoT, the book enables readers to develop specialized knowledge. Using concrete use cases and hands-on examples, readers will learn to apply machine learning to transform embedded and IoT systems. Overall, this indispensable guide provides a research-based foundation for leveraging machine learning in embedded systems.
+  </div>
+</div>
 
 </header>
 
diff --git a/training.html b/training.html
index a58e9d465..c53a81863 100644
--- a/training.html
+++ b/training.html
@@ -8,7 +8,7 @@
 
 <meta name="keywords" content="open-source, embedded systems, machine learning, tinyML">
 
-<title>Machine Learning Systems for TinyML - 8&nbsp; AI Training</title>
+<title>MACHINE LEARNING SYSTEMS for TinyML - 8&nbsp; AI Training</title>
 <style>
 code{white-space: pre-wrap;}
 span.smallcaps{font-variant: small-caps;}
@@ -92,20 +92,20 @@
   <nav id="quarto-sidebar" class="sidebar collapse collapse-horizontal sidebar-navigation floating overflow-auto">
     <div class="pt-lg-2 mt-2 text-left sidebar-header">
     <div class="sidebar-title mb-0 py-0">
-      <a href="./">Machine Learning Systems for TinyML</a> 
+      <a href="./">MACHINE LEARNING SYSTEMS for TinyML</a> 
         <div class="sidebar-tools-main tools-wide">
     <a href="https://github.com/harvard-edge/cs249r_book" rel="" title="Source Code" class="quarto-navigation-tool px-1" aria-label="Source Code"><i class="bi bi-github"></i></a>
     <div class="dropdown">
       <a href="" title="Download" id="quarto-navigation-tool-dropdown-0" class="quarto-navigation-tool dropdown-toggle px-1" data-bs-toggle="dropdown" aria-expanded="false" aria-label="Download"><i class="bi bi-download"></i></a>
       <ul class="dropdown-menu" aria-labelledby="quarto-navigation-tool-dropdown-0">
           <li>
-            <a class="dropdown-item sidebar-tools-main-item" href="./Machine-Learning-Systems-for-TinyML.pdf">
+            <a class="dropdown-item sidebar-tools-main-item" href="./MACHINE-LEARNING-SYSTEMS-for-TinyML.pdf">
               <i class="bi bi-bi-file-pdf pe-1"></i>
             Download PDF
             </a>
           </li>
           <li>
-            <a class="dropdown-item sidebar-tools-main-item" href="./Machine-Learning-Systems-for-TinyML.epub">
+            <a class="dropdown-item sidebar-tools-main-item" href="./MACHINE-LEARNING-SYSTEMS-for-TinyML.epub">
               <i class="bi bi-bi-journal pe-1"></i>
             Download ePub
             </a>
@@ -399,6 +399,12 @@ <h1 class="title"><span class="chapter-number">8</span>&nbsp; <span class="chapt
     
   </div>
   
+<div>
+  <div class="abstract">
+    <div class="abstract-title">Abstract</div>
+    Machine Learning Systems for TinyML offers comprehensive guidance on deploying machine learning on embedded devices. As edge computing and the Internet of Things proliferate, this textbook provides professionals and students the expertise to implement performant AI on resource-constrained hardware. A unique aspect of this book elucidates the entire machine learning workflow, from data engineering through training, optimization, acceleration, and production deployment. Key topics covered include deep learning and classical ML algorithms for embedded systems, efficient neural network architectures, hardware-aware training techniques, model compression, benchmarking for tinyML, and on-device learning. Additional chapters highlight cutting-edge advances like on-device data generation and crucial considerations around reliability, privacy, security, and responsible AI. With its rigorous approach spanning theory and practice across diverse tinyML application domains like smart homes, wearables, and industrial IoT, the book enables readers to develop specialized knowledge. Using concrete use cases and hands-on examples, readers will learn to apply machine learning to transform embedded and IoT systems. Overall, this indispensable guide provides a research-based foundation for leveraging machine learning in embedded systems.
+  </div>
+</div>
 
 </header>
 
diff --git a/workflow.html b/workflow.html
index d1854b109..cc1a90260 100644
--- a/workflow.html
+++ b/workflow.html
@@ -8,7 +8,7 @@
 
 <meta name="keywords" content="open-source, embedded systems, machine learning, tinyML">
 
-<title>Machine Learning Systems for TinyML - 5&nbsp; AI Workflow</title>
+<title>MACHINE LEARNING SYSTEMS for TinyML - 5&nbsp; AI Workflow</title>
 <style>
 code{white-space: pre-wrap;}
 span.smallcaps{font-variant: small-caps;}
@@ -92,20 +92,20 @@
   <nav id="quarto-sidebar" class="sidebar collapse collapse-horizontal sidebar-navigation floating overflow-auto">
     <div class="pt-lg-2 mt-2 text-left sidebar-header">
     <div class="sidebar-title mb-0 py-0">
-      <a href="./">Machine Learning Systems for TinyML</a> 
+      <a href="./">MACHINE LEARNING SYSTEMS for TinyML</a> 
         <div class="sidebar-tools-main tools-wide">
     <a href="https://github.com/harvard-edge/cs249r_book" rel="" title="Source Code" class="quarto-navigation-tool px-1" aria-label="Source Code"><i class="bi bi-github"></i></a>
     <div class="dropdown">
       <a href="" title="Download" id="quarto-navigation-tool-dropdown-0" class="quarto-navigation-tool dropdown-toggle px-1" data-bs-toggle="dropdown" aria-expanded="false" aria-label="Download"><i class="bi bi-download"></i></a>
       <ul class="dropdown-menu" aria-labelledby="quarto-navigation-tool-dropdown-0">
           <li>
-            <a class="dropdown-item sidebar-tools-main-item" href="./Machine-Learning-Systems-for-TinyML.pdf">
+            <a class="dropdown-item sidebar-tools-main-item" href="./MACHINE-LEARNING-SYSTEMS-for-TinyML.pdf">
               <i class="bi bi-bi-file-pdf pe-1"></i>
             Download PDF
             </a>
           </li>
           <li>
-            <a class="dropdown-item sidebar-tools-main-item" href="./Machine-Learning-Systems-for-TinyML.epub">
+            <a class="dropdown-item sidebar-tools-main-item" href="./MACHINE-LEARNING-SYSTEMS-for-TinyML.epub">
               <i class="bi bi-bi-journal pe-1"></i>
             Download ePub
             </a>
@@ -397,6 +397,12 @@ <h1 class="title"><span class="chapter-number">5</span>&nbsp; <span class="chapt
     
   </div>
   
+<div>
+  <div class="abstract">
+    <div class="abstract-title">Abstract</div>
+    Machine Learning Systems for TinyML offers comprehensive guidance on deploying machine learning on embedded devices. As edge computing and the Internet of Things proliferate, this textbook provides professionals and students the expertise to implement performant AI on resource-constrained hardware. A unique aspect of this book elucidates the entire machine learning workflow, from data engineering through training, optimization, acceleration, and production deployment. Key topics covered include deep learning and classical ML algorithms for embedded systems, efficient neural network architectures, hardware-aware training techniques, model compression, benchmarking for tinyML, and on-device learning. Additional chapters highlight cutting-edge advances like on-device data generation and crucial considerations around reliability, privacy, security, and responsible AI. With its rigorous approach spanning theory and practice across diverse tinyML application domains like smart homes, wearables, and industrial IoT, the book enables readers to develop specialized knowledge. Using concrete use cases and hands-on examples, readers will learn to apply machine learning to transform embedded and IoT systems. Overall, this indispensable guide provides a research-based foundation for leveraging machine learning in embedded systems.
+  </div>
+</div>
 
 </header>
 
diff --git a/zoo_datasets.html b/zoo_datasets.html
index 13a03cbf7..40beae115 100644
--- a/zoo_datasets.html
+++ b/zoo_datasets.html
@@ -8,7 +8,7 @@
 
 <meta name="keywords" content="open-source, embedded systems, machine learning, tinyML">
 
-<title>Machine Learning Systems for TinyML - Appendix B: Datasets</title>
+<title>MACHINE LEARNING SYSTEMS for TinyML - Appendix B: Datasets</title>
 <style>
 code{white-space: pre-wrap;}
 span.smallcaps{font-variant: small-caps;}
@@ -92,20 +92,20 @@
   <nav id="quarto-sidebar" class="sidebar collapse collapse-horizontal sidebar-navigation floating overflow-auto">
     <div class="pt-lg-2 mt-2 text-left sidebar-header">
     <div class="sidebar-title mb-0 py-0">
-      <a href="./">Machine Learning Systems for TinyML</a> 
+      <a href="./">MACHINE LEARNING SYSTEMS for TinyML</a> 
         <div class="sidebar-tools-main tools-wide">
     <a href="https://github.com/harvard-edge/cs249r_book" rel="" title="Source Code" class="quarto-navigation-tool px-1" aria-label="Source Code"><i class="bi bi-github"></i></a>
     <div class="dropdown">
       <a href="" title="Download" id="quarto-navigation-tool-dropdown-0" class="quarto-navigation-tool dropdown-toggle px-1" data-bs-toggle="dropdown" aria-expanded="false" aria-label="Download"><i class="bi bi-download"></i></a>
       <ul class="dropdown-menu" aria-labelledby="quarto-navigation-tool-dropdown-0">
           <li>
-            <a class="dropdown-item sidebar-tools-main-item" href="./Machine-Learning-Systems-for-TinyML.pdf">
+            <a class="dropdown-item sidebar-tools-main-item" href="./MACHINE-LEARNING-SYSTEMS-for-TinyML.pdf">
               <i class="bi bi-bi-file-pdf pe-1"></i>
             Download PDF
             </a>
           </li>
           <li>
-            <a class="dropdown-item sidebar-tools-main-item" href="./Machine-Learning-Systems-for-TinyML.epub">
+            <a class="dropdown-item sidebar-tools-main-item" href="./MACHINE-LEARNING-SYSTEMS-for-TinyML.epub">
               <i class="bi bi-bi-journal pe-1"></i>
             Download ePub
             </a>
@@ -383,6 +383,12 @@ <h1 class="title">Appendix B: Datasets</h1>
     
   </div>
   
+<div>
+  <div class="abstract">
+    <div class="abstract-title">Abstract</div>
+    Machine Learning Systems for TinyML offers comprehensive guidance on deploying machine learning on embedded devices. As edge computing and the Internet of Things proliferate, this textbook provides professionals and students the expertise to implement performant AI on resource-constrained hardware. A unique aspect of this book elucidates the entire machine learning workflow, from data engineering through training, optimization, acceleration, and production deployment. Key topics covered include deep learning and classical ML algorithms for embedded systems, efficient neural network architectures, hardware-aware training techniques, model compression, benchmarking for tinyML, and on-device learning. Additional chapters highlight cutting-edge advances like on-device data generation and crucial considerations around reliability, privacy, security, and responsible AI. With its rigorous approach spanning theory and practice across diverse tinyML application domains like smart homes, wearables, and industrial IoT, the book enables readers to develop specialized knowledge. Using concrete use cases and hands-on examples, readers will learn to apply machine learning to transform embedded and IoT systems. Overall, this indispensable guide provides a research-based foundation for leveraging machine learning in embedded systems.
+  </div>
+</div>
 
 </header>
 
diff --git a/zoo_models.html b/zoo_models.html
index 05f74063d..c2322e7ab 100644
--- a/zoo_models.html
+++ b/zoo_models.html
@@ -8,7 +8,7 @@
 
 <meta name="keywords" content="open-source, embedded systems, machine learning, tinyML">
 
-<title>Machine Learning Systems for TinyML - Appendix C: Model Zoo</title>
+<title>MACHINE LEARNING SYSTEMS for TinyML - Appendix C: Model Zoo</title>
 <style>
 code{white-space: pre-wrap;}
 span.smallcaps{font-variant: small-caps;}
@@ -92,20 +92,20 @@
   <nav id="quarto-sidebar" class="sidebar collapse collapse-horizontal sidebar-navigation floating overflow-auto">
     <div class="pt-lg-2 mt-2 text-left sidebar-header">
     <div class="sidebar-title mb-0 py-0">
-      <a href="./">Machine Learning Systems for TinyML</a> 
+      <a href="./">MACHINE LEARNING SYSTEMS for TinyML</a> 
         <div class="sidebar-tools-main tools-wide">
     <a href="https://github.com/harvard-edge/cs249r_book" rel="" title="Source Code" class="quarto-navigation-tool px-1" aria-label="Source Code"><i class="bi bi-github"></i></a>
     <div class="dropdown">
       <a href="" title="Download" id="quarto-navigation-tool-dropdown-0" class="quarto-navigation-tool dropdown-toggle px-1" data-bs-toggle="dropdown" aria-expanded="false" aria-label="Download"><i class="bi bi-download"></i></a>
       <ul class="dropdown-menu" aria-labelledby="quarto-navigation-tool-dropdown-0">
           <li>
-            <a class="dropdown-item sidebar-tools-main-item" href="./Machine-Learning-Systems-for-TinyML.pdf">
+            <a class="dropdown-item sidebar-tools-main-item" href="./MACHINE-LEARNING-SYSTEMS-for-TinyML.pdf">
               <i class="bi bi-bi-file-pdf pe-1"></i>
             Download PDF
             </a>
           </li>
           <li>
-            <a class="dropdown-item sidebar-tools-main-item" href="./Machine-Learning-Systems-for-TinyML.epub">
+            <a class="dropdown-item sidebar-tools-main-item" href="./MACHINE-LEARNING-SYSTEMS-for-TinyML.epub">
               <i class="bi bi-bi-journal pe-1"></i>
             Download ePub
             </a>
@@ -383,6 +383,12 @@ <h1 class="title">Appendix C: Model Zoo</h1>
     
   </div>
   
+<div>
+  <div class="abstract">
+    <div class="abstract-title">Abstract</div>
+    Machine Learning Systems for TinyML offers comprehensive guidance on deploying machine learning on embedded devices. As edge computing and the Internet of Things proliferate, this textbook provides professionals and students the expertise to implement performant AI on resource-constrained hardware. A unique aspect of this book elucidates the entire machine learning workflow, from data engineering through training, optimization, acceleration, and production deployment. Key topics covered include deep learning and classical ML algorithms for embedded systems, efficient neural network architectures, hardware-aware training techniques, model compression, benchmarking for tinyML, and on-device learning. Additional chapters highlight cutting-edge advances like on-device data generation and crucial considerations around reliability, privacy, security, and responsible AI. With its rigorous approach spanning theory and practice across diverse tinyML application domains like smart homes, wearables, and industrial IoT, the book enables readers to develop specialized knowledge. Using concrete use cases and hands-on examples, readers will learn to apply machine learning to transform embedded and IoT systems. Overall, this indispensable guide provides a research-based foundation for leveraging machine learning in embedded systems.
+  </div>
+</div>
 
 </header>