Deep Learning Reading

General

• Dynamic Routing Between Capsules(https://arxiv.org/abs/1710.0982)
• An Information-Theoretic View for Deep Learning. Jingwei Zhang, Tongliang Liu, and Dacheng Tao (http://arxiv.org/abs/1804.09060)

Computer Vision

• Deep Residual Learning for Image Recognition(https://arxiv.org/abs/1512.03385)
• Rich feature hierarchies for accurate object detection and semantic segmentation(https://arxiv.org/abs/1311.2524)

Conv net Visualization

• Deep Inside Convolutional Networks: Visualizing Image Classifiction Models and Saliency Maps

Natural Language Processing

• Seq2Seq-Vis: A Visual Debugging Tool for Sequence-to-Sequence Models. Hendrik Strobelt, Sebastian Gehrmann, Michael Behrisch, Adam Perer, Hanspeter Pfister, and Alexander M. Rush(http://arxiv.org/abs/1804.09299)

Deep Reinforcement Learning

Visual question answering papers

• A compositional Object-based Approach to Learning Physical Dynamics(https://arxiv.org/pdf/1612.00341.pdf)

Interpretable learning

• Learning to Compose Domain-Specific Transformations for Data Augmentation

Generative Modeling

• Generative Adversarial Text to Image Synthesis (https://arxiv.org/pdf/1605.05396.pdf)
• Wasserstein GAN (https://arxiv.org/abs/1701.07875)
• Towards Principled Methods for Training Generative Adversarial Networks (https://arxiv.org/abs/1701.04862)
• NIPS 2016 Tutorial: Generative Adversarial Networks (https://arxiv.org/abs/1701.00160)
• Boltzmann Encoded Adversarial Machines (https://arxiv.org/pdf/1804.08682.pdf)
• Realistic Evaluation of Deep Semi-Supervised Learning Algorithms (https://arxiv.org/abs/1804.09170)

GAN Papers

• Generative Adversarial Networks [Paper] (https://papers.nips.cc/paper/5423-generative-adversarial-nets.pdf)
• Generative Adversarial Networks as Variational Training of Energy Based Models arXiv
• Generative Adversarial Networks with Inverse Transformation Unit arXiv
• Generative Adversarial Parallelization [arXiv] (https://arxiv.org/abs/1612.04021)
• Generative Adversarial Residual Pairwise Networks for One Shot Learning arXiv
• Generative Adversarial Structured Networks Paper
• Generative Cooperative Net for Image Generation and Data Augmentation [https://arxiv.org/abs/1705.02887]
• Generative Moment Matching Networks [https://arxiv.org/abs/1502.02761]
• Generative Semantic Manipulation with Contrasting GAN [https://arxiv.org/abs/1708.00315]
• Geometric GAN [https://arxiv.org/abs/1705.02894]

Variational Autoencoder Papers

• Auto-Encoding Variational Bayes (https://arxiv.org/abs/1312.6114)
• Semi-supervised Learning with Deep Generative Models (https://arxiv.org/pdf/1406.5298.pdf)
• beta-VAE: Learning Basic visual concepts with constrained Varitional Framework(https://openreview.net/references/pdf?id=Sy2fzU9gl)
• beta-TCVAE: ISOLATING SOURCES OF DISENTANGLEMENT IN VARIATIONAL AUTOENCODERS(https://openreview.net/pdf?id=BJdMRoCIf)

Autoregreesive Models

• WaveNet: A Generative Model for Raw Audio [https://arxiv.org/abs/1609.03499]
• Parallel WaveNet: Fast High-Fidelity Speech Synthesis [https://arxiv.org/abs/1711.10433]

RNN related papers

• Bayesian Recurrent Neural Networks [https://arxiv.org/abs/1704.02798]
• Quasi-Recurrent Neural Networks [https://arxiv.org/abs/1611.01576]code

Interpretability realted papers

• Interpretable and Pedagogical Examples [https://arxiv.org/pdf/1711.00694.pdf]
• Understanding Black-box Predictions via Influence Functions [https://arxiv.org/abs/1703.04730]