Skip to content

Latest commit

 

History

History
executable file
·
146 lines (103 loc) · 11.4 KB

README.md

File metadata and controls

executable file
·
146 lines (103 loc) · 11.4 KB
Raw

DEEP LEARNING PAPERS

  • This repository contains my notes for various Deep learning papers
  • The codes are being shifted to ANOTHER REPO for sake of reducing redundancy

Note: Codes in Pytorch (Some are in fastai but will be ported to pure pytorch soon)

INDEX

MathBehind folder

  • This is an attempt to codify and understand the math behind Deep learning. Inspired from the Deep Learning book (Ian Goodfellow et al.)
  • All the explanations are in Jupyter Notebooks. (No README)
    • [1] Karush–Kuhn–Tucker

Main

[1] Alex Net

  • Krizhevsky, Alex, Ilya Sutskever, and Geoffrey E. Hinton. "Imagenet classification with deep convolutional neural networks." Advances in neural information processing systems. 2012 Paper

[2] VGG Net

  • Simonyan, Karen, and Andrew Zisserman. "Very deep convolutional networks for large-scale image recognition." arXiv preprint arXiv:1409.1556 (2014). Paper

[3] GoogLe Net

  • Szegedy, Christian, et al. "Going deeper with convolutions." Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2015. Paper

[4] Dropout

  • Srivastava, Nitish, et al. "Dropout: a simple way to prevent neural networks from overfitting." Journal of Machine Learning Research 15.1 (2014): 1929-1958. Paper

[5] Mobile Net

  • MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications (2017), Andrew G. Howard et al. Paper

[6] Inceptionism (Deep Dream)

  • Google Deep Dream Link

[7] DC GAN

  • Radford, A., Metz, L., & Chintala, S. (2015). Unsupervised representation learning with deep convolutional generative adversarial networks. arXiv preprint arXiv:1511.06434. Paper

[8] Spatial Transformer Networks

  • Jaderberg, M., Simonyan, K., & Zisserman, A. (2015). Spatial transformer networks. In Advances in neural information processing systems (pp. 2017-2025). Paper

[9] Squeeze Net

  • SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and< 1MB model size (2016), F. Iandola et al. Paper

[10] VAE (Auto-Encoding Variational Bayes)

  • Kingma, D. P., & Welling, M. (2013). Auto-encoding variational bayes. arXiv preprint arXiv:1312.6114. Paper

[11] SRCNN

  • Dong, C., Loy, C. C., He, K., & Tang, X. (2014, September). Learning a deep convolutional network for image super-resolution. In European conference on computer vision (pp. 184-199). Springer, Cham. Paper

[12] WGAN

  • Arjovsky, M., Chintala, S., & Bottou, L. (2017). Wasserstein gan. arXiv preprint arXiv:1701.07875. Paper

[13] One cycle

  • Smith, L. N. (2017, March). Cyclical learning rates for training neural networks. In 2017 IEEE Winter Conference on Applications of Computer Vision (WACV) (pp. 464-472). IEEE. Paper

[14] A disciplined approach to neural network hyper-parameters

  • Smith, L. N. (2018). A disciplined approach to neural network hyper-parameters: Part 1--learning rate, batch size, momentum, and weight decay. arXiv preprint arXiv:1803.09820. Paper

[15] Class Imbalance Problem

  • Buda, M., Maki, A., & Mazurowski, M. A. (2018). A systematic study of the class imbalance problem in convolutional neural networks. Neural Networks, 106, 249-259. Paper

[16] Perceptual Loss (For super resolution)

  • Johnson, J., Alahi, A., & Fei-Fei, L. (2016, October). Perceptual losses for real-time style transfer and super-resolution. In European conference on computer vision (pp. 694-711). Springer, Cham. Paper

[17] Semantic segmentation DeepLab

  • Chen, L. C., Papandreou, G., Kokkinos, I., Murphy, K., & Yuille, A. L. (2017). Deeplab: Semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected crfs. IEEE transactions on pattern analysis and machine intelligence, 40(4), 834-848. Paper

[18] Neural Fabrics(WIP)

  • Saxena, S., & Verbeek, J. (2016). Convolutional neural fabrics. In Advances in Neural Information Processing Systems (pp. 4053-4061).

[19] Focal Loss

  • Lin, T. Y., Goyal, P., Girshick, R., He, K., & Dollár, P. (2017). Focal loss for dense object detection. In Proceedings of the IEEE international conference on computer vision (pp. 2980-2988). Paper

[20] Thinking machines - Turing

  • A. M. TURING, I.—COMPUTING MACHINERY AND INTELLIGENCE, Mind, Volume LIX, Issue 236, October 1950, Pages 433–460. Paper

[21] Unets

  • Ronneberger, O., Fischer, P., & Brox, T. (2015, October). U-net: Convolutional networks for biomedical image segmentation. In International Conference on Medical image computing and computer-assisted intervention (pp. 234-241). Springer, Cham. Paper

[22] LSTM

  • Hochreiter, S., & Schmidhuber, J. (1997). Long short-term memory. Neural computation, 9(8), 1735-1780.Paper

[23] SELU

  • Klambauer, G., Unterthiner, T., Mayr, A., & Hochreiter, S. (2017). Self-normalizing neural networks. In Advances in neural information processing systems (pp. 971-980). Paper

[24] swish

  • Ramachandran, P., Zoph, B., & Le, Q. V. (2017). Searching for activation functions. arXiv preprint arXiv:1710.05941. Paper

[24] Bag Of Tricks

  • He, T., Zhang, Z., Zhang, H., Zhang, Z., Xie, J., & Li, M. (2019). Bag of tricks for image classification with convolutional neural networks. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (pp. 558-567). Paper

[25] Vanilla GNN (WIP)

[26] Singing voice separation with deep U-Net (WIP)

  • Jansson, A., Humphrey, E., Montecchio, N., Bittner, R., Kumar, A., & Weyde, T. (2017). Singing voice separation with deep U-Net convolutional networks. Paper

[27] HRNet (WIP)

  • Wang, J., Sun, K., Cheng, T., Jiang, B., Deng, C., Zhao, Y., ... & Liu, W. (2020). Deep high-resolution representation learning for visual recognition. IEEE transactions on pattern analysis and machine intelligence. Paper

[28] Understanding Deep learning requires rethinking generalization) (Just notes

  • Zhang, C., Bengio, S., Hardt, M., Recht, B., & Vinyals, O. (2016). Understanding deep learning requires rethinking generalization. arXiv preprint arXiv:1611.03530. Paper

[29] NVAE (WIP)

  • Vahdat, A., & Kautz, J. (2020). NVAE: A Deep Hierarchical Variational Autoencoder. arXiv preprint arXiv:2007.03898. Paper

[30] DRL and neuroscience

  • Botvinick, M., Wang, J. X., Dabney, W., Miller, K. J., & Kurth-Nelson, Z. (2020). Deep Reinforcement Learning and Its Neuroscientific Implications. Neuron. Paper

[31] Computational Limits

  • Thompson, N. C., Greenewald, K., Lee, K., & Manso, G. F. (2020). The Computational Limits of Deep Learning. arXiv preprint arXiv:2007.05558. Paper

[32] What is the state of pruning

  • Blalock, D., Ortiz, J. J. G., Frankle, J., & Guttag, J. (2020). What is the state of neural network pruning?. arXiv preprint arXiv:2003.03033. Paper

[33] Super Resolution using Sub Pixel Convolutions

  • Shi, W., Caballero, J., Huszár, F., Totz, J., Aitken, A. P., Bishop, R., ... & Wang, Z. (2016). Real-time single image and video super-resolution using an efficient sub-pixel convolutional neural network. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 1874-1883). Paper

[34] Google Keyboard Federated Learning(Notes only. refer to [35] for code)

  • Chen, M., Mathews, R., Ouyang, T., & Beaufays, F. (2019). Federated learning of out-of-vocabulary words. arXiv preprint arXiv:1903.10635. Paper

[35] Federated Learning (original paper)

  • Konečný, J., McMahan, H. B., Yu, F. X., Richtárik, P., Suresh, A. T., & Bacon, D. (2016). Federated learning: Strategies for improving communication efficiency. arXiv preprint arXiv:1610.05492. Paper

[36] LightSeg (only notes for now)

  • Emara, T., Abd El Munim, H. E., & Abbas, H. M. (2019, December). LiteSeg: A Novel Lightweight ConvNet for Semantic Segmentation. In 2019 Digital Image Computing: Techniques and Applications (DICTA) (pp. 1-7). IEEE. (Link

[37] Training BatchNorm only Batchnorm

  • Frankle, J., Schwab, D. J., & Morcos, A. S. (2020). Training BatchNorm and Only BatchNorm: On the Expressive Power of Random Features in CNNs. arXiv preprint arXiv:2003.00152. Paper

[38] Mish

  • Misra, D. (2019). Mish: A self regularized non-monotonic neural activation function. arXiv preprint arXiv:1908.08681. paper

[39] ShuffleNet (WIP)

  • Zhang, X., Zhou, X., Lin, M., & Sun, J. (2018). Shufflenet: An extremely efficient convolutional neural network for mobile devices. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 6848-6856). Paper