CNN及其可解释性

https://stats385.github.io/readings

https://arxiv.org/pdf/1311.2901.pdf

A Mathematical Theory of Deep Convolutional Neural Networks for Feature Extraction

https://www.nari.ee.ethz.ch/commth//pubs/files/deep-2016.pdf

https://calculatedcontent.com/2017/02/24/why-deep-learning-works-3-backprop-minimizes-the-free-energy/

http://yann.lecun.com/exdb/publis/pdf/lecun-06.pdf

https://calculatedcontent.com/2015/03/25/why-does-deep-learning-work/

https://calculatedcontent.com/2015/04/01/why-deep-learning-works-ii-the-renormalization-group/

https://pdfs.semanticscholar.org/a0d1/6f0e99f7ce5e6fb70b1a68c685e9ad610657.pdf?_ga=2.60835948.1949072808.1537707280-971327580.1499580321

https://www.semanticscholar.org/paper/A-Learning-Algorithm-for-Boltzmann-Machines-Ackley-Hinton/2e3e09e48a7a62dc30efd8ef7fc4665a53e84d7a

https://www.quora.com/What-is-a-convolutional-neural-network

https://distill.pub/2017/feature-visualization/

https://colah.github.io/posts/2014-07-Conv-Nets-Modular/

http://neuralnetworksanddeeplearning.com/chap6.html

http://kvfrans.com/visualizing-features-from-a-convolutional-neural-network/

https://distill.pub/2018/building-blocks/

https://cs231n.github.io/neural-networks-1/

https://distill.pub/2016/deconv-checkerboard/

https://www.tensorflow.org/tutorials/images/deep_cnn

https://www.coursera.org/learn/convolutional-neural-networks

Unsupervised representation learning with deep convolutional generative adversarial networks  [PDF]025

 

1. Inceptionism: Going deeper into neural networks  [HTML]
   Mordvintsev, A., Olah, C. and Tyka, M., 2015. Google Research Blog. Retrieved June, Vol 20.
2. https://github.com/google/deepdream/blob/master/dream.ipynb
3. Geodesics of learned representations  [PDF]
   Henaff, O.J. and Simoncelli, E.P., 2015. arXiv preprint arXiv:1511.06394.
4. DeepDreaming with TensorFlow  [link]

1. A guide to convolution arithmetic for deep learning  [PDF]

1. Dumoulin, V. and Visin, F., 2016. arXiv preprint arXiv:1603.07285.
2. Is the deconvolution layer the same as a convolutional layer?  [PDF]
   Shi, W., Caballero, J., Theis, L., Huszar, F., Aitken, A., Ledig, C. and Wang, Z., 2016. arXiv preprint arXiv:1609.07009.
3. Conditional generative adversarial nets for convolutional face generation  [PDF]
   Gauthier, J., 2014. Class Project for Stanford CS231N: Convolutional Neural Networks for Visual Recognition, Winter semester, Vol 2014.