Process tutorial notebooks

NeuromatchAcademy · Dec 20, 2023 · 326ec51 · 326ec51
1 parent 83497b1
commit 326ec51
Show file tree

Hide file tree

Showing 5 changed files with 4 additions and 8 deletions.
diff --git a/tutorials/Bonus_Autoencoders/Bonus_Tutorial1.ipynb b/tutorials/Bonus_Autoencoders/Bonus_Tutorial1.ipynb
@@ -2305,7 +2305,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.9.17"
+   "version": "3.9.18"
   }
  },
  "nbformat": 4,

diff --git a/tutorials/Bonus_Autoencoders/instructor/Bonus_Tutorial1.ipynb b/tutorials/Bonus_Autoencoders/instructor/Bonus_Tutorial1.ipynb
@@ -46,8 +46,6 @@
     "\n",
     "The primary task is to reconstruct output images based on a compressed representation of the inputs. This task teaches the network which details to throw away while still producing images that are similar to the inputs.\n",
     "\n",
-    "&nbsp;\n",
-    "\n",
     "A fictitious *MNIST cognitive task* bundles more elaborate tasks such as removing noise from images, guessing occluded parts, and recovering original image orientation. We use the handwritten digits from the MNIST dataset since it is easier to identify similar images or issues with reconstructions than in other types of data, such as spiking data time series.\n",
     "\n",
     "&nbsp;\n",
@@ -2313,7 +2311,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.9.17"
+   "version": "3.9.18"
   }
  },
  "nbformat": 4,

diff --git a/tutorials/Bonus_Autoencoders/static/Bonus_Tutorial1_Solution_9d6c1017_11.png b/tutorials/Bonus_Autoencoders/static/Bonus_Tutorial1_Solution_9d6c1017_11.png
diff --git a/tutorials/Bonus_Autoencoders/static/Bonus_Tutorial1_Solution_c05ddd88_0.png b/tutorials/Bonus_Autoencoders/static/Bonus_Tutorial1_Solution_c05ddd88_0.png
diff --git a/tutorials/Bonus_Autoencoders/student/Bonus_Tutorial1.ipynb b/tutorials/Bonus_Autoencoders/student/Bonus_Tutorial1.ipynb
@@ -46,8 +46,6 @@
     "\n",
     "The primary task is to reconstruct output images based on a compressed representation of the inputs. This task teaches the network which details to throw away while still producing images that are similar to the inputs.\n",
     "\n",
-    "&nbsp;\n",
-    "\n",
     "A fictitious *MNIST cognitive task* bundles more elaborate tasks such as removing noise from images, guessing occluded parts, and recovering original image orientation. We use the handwritten digits from the MNIST dataset since it is easier to identify similar images or issues with reconstructions than in other types of data, such as spiking data time series.\n",
     "\n",
     "&nbsp;\n",
@@ -1173,7 +1171,7 @@
     "\n",
     "*Example output:*\n",
     "\n",
-    "<img alt='Solution hint' align='left' width=1127.0 height=578.0 src=https://raw.githubusercontent.com/NeuromatchAcademy/course-content/main/tutorials/Bonus_Autoencoders/static/Bonus_Tutorial1_Solution_c05ddd88_0.png>\n",
+    "<img alt='Solution hint' align='left' width=1132.0 height=575.0 src=https://raw.githubusercontent.com/NeuromatchAcademy/course-content/main/tutorials/Bonus_Autoencoders/static/Bonus_Tutorial1_Solution_c05ddd88_0.png>\n",
     "\n"
    ]
   },
@@ -2254,7 +2252,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.9.17"
+   "version": "3.9.18"
   }
  },
  "nbformat": 4,