Article files.

Author: codeandfire

README.md

@@ -0,0 +1,20 @@
+This is a short tutorial describing how backpropagation is performed in a convolutional neural network.
+
+Backpropagation through the convolution and max pooling operations of a convolutional network seems like a mathematical nightmare, which is best left to the deep learning libraries to perform under-the-hood!
+However, on a closer look, you realize that it is not as complicated as you first imagined, and the expressions turn out to have a neat and elegant form.
+
+You can read this article as a PDF by compiling the files `cnn_backprop.tex` and `cnn_backprop.bib`.
+For example, you could use a tool such as [Latexmk](https://mg.readthedocs.io/latexmk.html):
+```
+$ latexmk -pdf
+```
+
+If you use this article in your work, please cite it as follows:
+```bibtex
+@misc{cnnbackprop,
+  author={Maheshwari, Saniya},
+  title={Backpropagation in convolutional networks},
+  howpublished={\url{https://github.com/codeandfire/cnn-backprop}},
+  year={2021},
+}
+```

cnn_backprop.bib

@@ -0,0 +1,62 @@
+@article{dumoulin2016guide,
+	author = {Dumoulin, Vincent and Visin, Francesco},
+	journal = {arXiv preprint arXiv:1603.07285},
+	title = {A guide to convolution arithmetic for deep learning},
+	year = {2016}}
+
+@inproceedings{zeiler2014visualizing,
+	author = {Zeiler, Matthew D and Fergus, Rob},
+	booktitle = {European conference on computer vision},
+	organization = {Springer},
+	pages = {818--833},
+	title = {Visualizing and understanding convolutional networks},
+	year = {2014}}
+
+@book{goodfellow2016deep,
+	author = {Goodfellow, Ian and Bengio, Yoshua and Courville, Aaron},
+	publisher = {MIT press},
+	title = {Deep learning},
+	year = {2016}}
+
+@misc{pytorchsourcecode,
+	author = {PyTorch Team},
+	note = {Accessed: 2021-07-14.},
+	title = {torch/nn/grad.py},
+	url = {https://github.com/pytorch/pytorch/blob/master/torch/nn/grad.py#L165},
+	bdsk-url-1 = {https://github.com/pytorch/pytorch/blob/master/torch/nn/grad.py#L165}}
+
+@article{simonyan2013deep,
+	author = {Simonyan, Karen and Vedaldi, Andrea and Zisserman, Andrew},
+	journal = {arXiv preprint arXiv:1312.6034},
+	title = {Deep inside convolutional networks: Visualising image classification models and saliency maps},
+	year = {2013}}
+
+@article{krizhevsky2012imagenet,
+	author = {Krizhevsky, Alex and Sutskever, Ilya and Hinton, Geoffrey E},
+	journal = {Advances in neural information processing systems},
+	pages = {1097--1105},
+	title = {Imagenet classification with deep convolutional neural networks},
+	volume = {25},
+	year = {2012}}
+
+@inproceedings{zeiler2010deconvolutional,
+	author = {Zeiler, Matthew D and Krishnan, Dilip and Taylor, Graham W and Fergus, Rob},
+	booktitle = {2010 IEEE Computer Society Conference on computer vision and pattern recognition},
+	organization = {IEEE},
+	pages = {2528--2535},
+	title = {Deconvolutional networks},
+	year = {2010}}
+
+@inproceedings{long2015fully,
+	author = {Long, Jonathan and Shelhamer, Evan and Darrell, Trevor},
+	booktitle = {Proceedings of the IEEE conference on computer vision and pattern recognition},
+	pages = {3431--3440},
+	title = {Fully convolutional networks for semantic segmentation},
+	year = {2015}}
+
+@misc{kafunah2016backpropagation,
+	author = {Kafunah, Jefkine},
+	note = {Accessed: 2021-07-14},
+	title = {Backpropagation in Convolutional Neural Networks},
+	url = {https://jefkine.com/general/2016/09/05/backpropagation-in-convolutional-neural-networks/},
+	bdsk-url-1 = {https://jefkine.com/general/2016/09/05/backpropagation-in-convolutional-neural-networks/}}