Merge branch 'dev'

harvard-edge · Jan 11, 2025 · 517d335 · 517d335
2 parents 0538454 + 4f813b8
commit 517d335
Show file tree

Hide file tree

Showing 12 changed files with 1,926 additions and 898 deletions.
diff --git a/.all-contributorsrc b/.all-contributorsrc
diff --git a/README.md b/README.md
diff --git a/contents/core/data_engineering/data_engineering.bib b/contents/core/data_engineering/data_engineering.bib
diff --git a/contents/core/data_engineering/data_engineering.qmd b/contents/core/data_engineering/data_engineering.qmd
diff --git a/contents/core/data_engineering/images/png/data_pipeline.png b/contents/core/data_engineering/images/png/data_pipeline.png
diff --git a/contents/core/data_engineering/images/png/dataset_myopia.png b/contents/core/data_engineering/images/png/dataset_myopia.png
diff --git a/contents/core/dl_primer/dl_primer.bib b/contents/core/dl_primer/dl_primer.bib
diff --git a/contents/core/dnn_architectures/dnn_architectures.bib b/contents/core/dnn_architectures/dnn_architectures.bib
@@ -1,155 +1,239 @@
 @book{reagen2017deep,
-	title        = {Deep learning for computer architects},
-	author       = {Reagen, Brandon and Adolf, Robert and Whatmough, Paul and Wei, Gu-Yeon and Brooks, David and Martonosi, Margaret},
-	year         = 2017,
-	publisher    = {Springer}
-}
+  doi = {10.1007/978-3-031-01756-8},
+  source = {Crossref},
+  author = {Reagen, Brandon and Adolf, Robert and Whatmough, Paul and Wei, Gu-Yeon and Brooks, David},
+  year = {2017},
+  isbn = {9783031006289,9783031017568},
+  url = {https://doi.org/10.1007/978-3-031-01756-8},
+  issn = {1935-3235,1935-3243},
+  publisher = {Springer International Publishing},
+  title = {Deep Learning for Computer Architects},
+}
+
 @article{hornik1989multilayer,
-	title        = {Multilayer feedforward networks are universal approximators},
-	author       = {Hornik, Kurt and Stinchcombe, Maxwell and White, Halbert},
-	year         = 1989,
-	journal      = {Neural networks},
-	publisher    = {Elsevier},
-	volume       = 2,
-	number       = 5,
-	pages        = {359--366}
-}
+  number = {5},
+  doi = {10.1016/0893-6080(89)90020-8},
+  pages = {359--366},
+  source = {Crossref},
+  volume = {2},
+  author = {Hornik, Kurt and Stinchcombe, Maxwell and White, Halbert},
+  year = {1989},
+  month = jan,
+  url = {https://doi.org/10.1016/0893-6080(89)90020-8},
+  issn = {0893-6080},
+  journal = {Neural Networks},
+  publisher = {Elsevier BV},
+  title = {Multilayer feedforward networks are universal approximators},
+}
+
 @article{cybenko1989approximation,
-	title        = {Approximation by superpositions of a sigmoidal function},
-	author       = {Cybenko, George},
-	year         = 1989,
-	journal      = {Mathematics of control, signals and systems},
-	publisher    = {Springer},
-	volume       = 2,
-	number       = 4,
-	pages        = {303--314}
-}
+  number = {4},
+  doi = {10.1007/bf02134016},
+  pages = {455--455},
+  source = {Crossref},
+  volume = {5},
+  author = {Cybenko, G.},
+  year = {1992},
+  month = dec,
+  url = {https://doi.org/10.1007/bf02134016},
+  issn = {0932-4194,1435-568X},
+  journal = {Mathematics of Control, Signals, and Systems},
+  publisher = {Springer Science and Business Media LLC},
+  title = {Approximation by superpositions of a sigmoidal function},
+}
+
 @article{lecun1989backpropagation,
-	title        = {Backpropagation applied to handwritten zip code recognition},
-	author       = {LeCun, Yann and Boser, Bernhard and Denker, John S and Henderson, Donnie and Howard, Richard E and Hubbard, Wayne and Jackel, Lawrence D},
-	year         = 1989,
-	journal      = {Neural Computation},
-	publisher    = {MIT Press},
-	volume       = 1,
-	number       = 4,
-	pages        = {541--551}
-}
-@article{elman1990finding,
-	title        = {Finding structure in time},
-	author       = {Elman, Jeffrey L},
-	year         = 1990,
-	journal      = {Cognitive Science},
-	publisher    = {Elsevier},
-	volume       = 14,
-	number       = 2,
-	pages        = {179--211}
-}
-@article{vaswani2017attention,
-	title        = {Attention is all you need},
-	author       = {Vaswani, Ashish and Shazeer, Noam and Parmar, Niki and Uszkoreit, Jakob and Jones, Llion and Gomez, Aidan N and Kaiser, Lukasz and Polosukhin, Illia},
-	year         = 2017,
-	journal      = {Advances in Neural Information Processing Systems},
-	booktitle    = {Advances in Neural Information Processing Systems},
-	volume       = 30,
-	pages        = {5998--6008}
-}
+  number = {4},
+  doi = {10.1162/neco.1989.1.4.541},
+  pages = {541--551},
+  source = {Crossref},
+  volume = {1},
+  author = {LeCun, Y. and Boser, B. and Denker, J. S. and Henderson, D. and Howard, R. E. and Hubbard, W. and Jackel, L. D.},
+  year = {1989},
+  month = dec,
+  url = {https://doi.org/10.1162/neco.1989.1.4.541},
+  issn = {0899-7667,1530-888X},
+  journal = {Neural Computation},
+  publisher = {MIT Press},
+  title = {Backpropagation Applied to Handwritten Zip Code Recognition},
+}
+
+@incollection{elman1990finding,
+  doi = {10.7551/mitpress/1888.003.0015},
+  pages = {257--288},
+  source = {Crossref},
+  author = {Elman, Jeffrey L.},
+  year = {2002},
+  month = sep,
+  isbn = {9780262281744},
+  url = {https://doi.org/10.7551/mitpress/1888.003.0015},
+  booktitle = {Cognitive Modeling},
+  publisher = {The MIT Press},
+  title = {Finding Structure in Time},
+  journal = {Cognitive Science},
+  volume = {14},
+  number = {2},
+}
+
+@inproceedings{vaswani2017attention,
+  doi = {10.18653/v1/p18-1008},
+  source = {Crossref},
+  author = {Chen, Mia Xu and Firat, Orhan and Bapna, Ankur and Johnson, Melvin and Macherey, Wolfgang and Foster, George and Jones, Llion and Schuster, Mike and Shazeer, Noam and Parmar, Niki and Vaswani, Ashish and Uszkoreit, Jakob and Kaiser, Lukasz and Chen, Zhifeng and Wu, Yonghui and Hughes, Macduff},
+  year = {2018},
+  url = {https://doi.org/10.18653/v1/p18-1008},
+  booktitle = {Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)},
+  publisher = {Association for Computational Linguistics},
+  title = {The Best of Both Worlds: Combining Recent Advances in Neural Machine Translation},
+  journal = {Advances in Neural Information Processing Systems},
+  volume = {30},
+  pages = {5998--6008},
+}
+
 @article{lecun2015deep,
-	title        = {Deep learning},
-	author       = {LeCun, Yann and Bengio, Yoshua and Hinton, Geoffrey},
-	year         = 2015,
-	journal      = {Nature},
-	publisher    = {Nature Publishing Group},
-	volume       = 521,
-	number       = 7553,
-	pages        = {436--444}
-}
+  number = {7553},
+  doi = {10.1038/nature14539},
+  pages = {436--444},
+  source = {Crossref},
+  volume = {521},
+  author = {LeCun, Yann and Bengio, Yoshua and Hinton, Geoffrey},
+  year = {2015},
+  month = may,
+  url = {https://doi.org/10.1038/nature14539},
+  issn = {0028-0836,1476-4687},
+  journal = {Nature},
+  publisher = {Springer Science and Business Media LLC},
+  title = {Deep learning},
+}
+
 @article{rosenblatt1958perceptron,
-	title        = {The perceptron: A probabilistic model for information storage and organization in the brain},
-	author       = {Rosenblatt, Frank},
-	year         = 1958,
-	journal      = {Psychological review},
-	publisher    = {American Psychological Association},
-	volume       = 65,
-	number       = 6,
-	pages        = 386
-}
+  number = {6},
+  doi = {10.1037/h0042519},
+  pages = {386--408},
+  source = {Crossref},
+  volume = {65},
+  author = {Rosenblatt, F.},
+  year = {1958},
+  url = {https://doi.org/10.1037/h0042519},
+  issn = {1939-1471,0033-295X},
+  journal = {Psychological Review},
+  publisher = {American Psychological Association (APA)},
+  title = {The perceptron: A probabilistic model for information storage and organization in the brain.},
+}
+
 @article{rumelhart1986learning,
-	title        = {Learning representations by back-propagating errors},
-	author       = {Rumelhart, David E and Hinton, Geoffrey E and Williams, Ronald J},
-	year         = 1986,
-	journal      = {Nature},
-	publisher    = {Nature Publishing Group},
-	volume       = 323,
-	number       = 6088,
-	pages        = {533--536}
-}
+  number = {6088},
+  doi = {10.1038/323533a0},
+  pages = {533--536},
+  source = {Crossref},
+  volume = {323},
+  author = {Rumelhart, David E. and Hinton, Geoffrey E. and Williams, Ronald J.},
+  year = {1986},
+  month = oct,
+  url = {https://doi.org/10.1038/323533a0},
+  issn = {0028-0836,1476-4687},
+  journal = {Nature},
+  publisher = {Springer Science and Business Media LLC},
+  title = {Learning representations by back-propagating errors},
+}
+
 @article{lecun1998gradient,
-	title        = {Gradient-based learning applied to document recognition},
-	author       = {LeCun, Yann and Bottou, L{\'e}on and Bengio, Yoshua and Haffner, Patrick},
-	year         = 1998,
-	journal      = {Proceedings of the IEEE},
-	publisher    = {IEEE},
-	volume       = 86,
-	number       = 11,
-	pages        = {2278--2324}
-}
-@article{he2016deep,
-	title        = {Deep residual learning for image recognition},
-	author       = {He, Kaiming and Zhang, Xiangyu and Ren, Shaoqing and Sun, Jian},
-	year         = 2016,
-	journal      = {Proceedings of the IEEE conference on computer vision and pattern recognition},
-	pages        = {770--778}
-}
+  number = {11},
+  doi = {10.1109/5.726791},
+  pages = {2278--2324},
+  source = {Crossref},
+  volume = {86},
+  author = {Lecun, Y. and Bottou, L. and Bengio, Y. and Haffner, P.},
+  year = {1998},
+  url = {https://doi.org/10.1109/5.726791},
+  issn = {0018-9219},
+  journal = {Proceedings of the IEEE},
+  publisher = {Institute of Electrical and Electronics Engineers (IEEE)},
+  title = {Gradient-based learning applied to document recognition},
+}
+
+@inproceedings{he2016deep,
+  doi = {10.1109/cvpr.2016.90},
+  source = {Crossref},
+  author = {He, Kaiming and Zhang, Xiangyu and Ren, Shaoqing and Sun, Jian},
+  year = {2016},
+  month = jun,
+  url = {https://doi.org/10.1109/cvpr.2016.90},
+  booktitle = {2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
+  publisher = {IEEE},
+  title = {Deep Residual Learning for Image Recognition},
+  journal = {Proceedings of the IEEE conference on computer vision and pattern recognition},
+  pages = {770--778},
+}
+
 @article{ioffe2015batch,
-	title        = {Batch normalization: Accelerating deep network training by reducing internal covariate shift},
-	author       = {Ioffe, Sergey and Szegedy, Christian},
-	year         = 2015,
-	journal      = {International conference on machine learning},
-	pages        = {448--456},
-	organization = {PMLR}
-}
+  title = {Batch normalization: Accelerating deep network training by reducing internal covariate shift},
+  author = {Ioffe, Sergey and Szegedy, Christian},
+  year = {2015},
+  journal = {International conference on machine learning},
+  pages = {448--456},
+  organization = {PMLR},
+}
+
 @article{ba2016layer,
-	title        = {Layer normalization},
-	author       = {Ba, Jimmy Lei and Kiros, Jamie Ryan and Hinton, Geoffrey E},
-	year         = 2016,
-	journal      = {arXiv preprint arXiv:1607.06450}
-}
+  url = {http://arxiv.org/abs/1607.06450v1},
+  year = {2016},
+  month = jul,
+  title = {Layer Normalization},
+  author = {Ba, Jimmy Lei and Kiros, Jamie Ryan and Hinton, Geoffrey E.},
+  primaryclass = {stat.ML},
+  archiveprefix = {arXiv},
+  journal = {arXiv preprint arXiv:1607.06450},
+}
+
 @article{hochreiter1997long,
-	title        = {Long short-term memory},
-	author       = {Hochreiter, Sepp and Schmidhuber, J{\"u}rgen},
-	year         = 1997,
-	journal      = {Neural computation},
-	publisher    = {MIT Press},
-	volume       = 9,
-	number       = 8,
-	pages        = {1735--1780}
-}
+  number = {8},
+  doi = {10.1162/neco.1997.9.8.1735},
+  pages = {1735--1780},
+  source = {Crossref},
+  volume = {9},
+  author = {Hochreiter, Sepp and Schmidhuber, J\"urgen},
+  year = {1997},
+  month = nov,
+  url = {https://doi.org/10.1162/neco.1997.9.8.1735},
+  issn = {0899-7667,1530-888X},
+  journal = {Neural Computation},
+  publisher = {MIT Press},
+  title = {Long Short-Term Memory},
+}
+
 @inproceedings{cho2014properties,
-	title        = {On the properties of neural machine translation: Encoder-decoder approaches},
-	author       = {Cho, Kyunghyun and van Merrienboer, Bart and Bahdanau, Dzmitry and Bengio, Yoshua},
-	year         = 2014,
-	booktitle    = {Eighth Workshop on Syntax, Semantics and Structure in Statistical Translation (SSST-8)},
-	pages        = {103--111},
-	organization = {Association for Computational Linguistics}
-}
+  title = {On the properties of neural machine translation: Encoder-decoder approaches},
+  author = {Cho, Kyunghyun and van Merrienboer, Bart and Bahdanau, Dzmitry and Bengio, Yoshua},
+  year = {2014},
+  booktitle = {Eighth Workshop on Syntax, Semantics and Structure in Statistical Translation (SSST-8)},
+  pages = {103--111},
+  organization = {Association for Computational Linguistics},
+}
+
 @article{bahdanau2014neural,
-	title        = {Neural machine translation by jointly learning to align and translate},
-	author       = {Bahdanau, Dzmitry and Cho, Kyunghyun and Bengio, Yoshua},
-	year         = 2014,
-	journal      = {arXiv preprint arXiv:1409.0473},
-	booktitle    = {Proceedings of the International Conference on Learning Representations (ICLR)}
-}
+  url = {http://arxiv.org/abs/1409.0473v7},
+  year = {2014},
+  month = sep,
+  title = {Neural Machine Translation by Jointly Learning to Align and Translate},
+  author = {Bahdanau, Dzmitry and Cho, Kyunghyun and Bengio, Yoshua},
+  primaryclass = {cs.CL},
+  archiveprefix = {arXiv},
+  journal = {arXiv preprint arXiv:1409.0473},
+  booktitle = {Proceedings of the International Conference on Learning Representations (ICLR)},
+}
+
 @article{dosovitskiy2021image,
-	title        = {An image is worth 16x16 words: Transformers for image recognition at scale},
-	author       = {Dosovitskiy, Alexey and Beyer, Lucas and Kolesnikov, Alexander and Weissenborn, Dirk and Zhai, Xiaohua and Unterthiner, Thomas and Dehghani, Mostafa and Minderer, Matthias and Heigold, Georg and Gelly, Sylvain and others},
-	year         = 2021,
-	journal      = {International Conference on Learning Representations}
+  title = {An image is worth 16x16 words: Transformers for image recognition at scale},
+  author = {Dosovitskiy, Alexey and Beyer, Lucas and Kolesnikov, Alexander and Weissenborn, Dirk and Zhai, Xiaohua and Unterthiner, Thomas and Dehghani, Mostafa and Minderer, Matthias and Heigold, Georg and Gelly, Sylvain and others},
+  year = {2021},
+  journal = {International Conference on Learning Representations},
 }
+
 @article{brown2020language,
-	title        = {Language models are few-shot learners},
-	author       = {Brown, Tom B and Mann, Benjamin and Ryder, Nick and Subbiah, Melanie and Kaplan, Jared and Dhariwal, Prafulla and Neelakantan, Arvind and Shyam, Pranav and Sastry, Girish and Askell, Amanda and others},
-	year         = 2020,
-	journal      = {Advances in Neural Information Processing Systems},
-	volume       = 33,
-	pages        = {1877--1901}
-}
+  title = {Language models are few-shot learners},
+  author = {Brown, Tom B and Mann, Benjamin and Ryder, Nick and Subbiah, Melanie and Kaplan, Jared and Dhariwal, Prafulla and Neelakantan, Arvind and Shyam, Pranav and Sastry, Girish and Askell, Amanda and others},
+  year = {2020},
+  journal = {Advances in Neural Information Processing Systems},
+  volume = {33},
+  pages = {1877--1901},
+}