Papers

• Auto-Encoding Variational Bayes, Diederik P Kingma, Max Welling

• Tutorial on Variational Autoencoders, Carl Doersch

• WGAN, Martin Arjovsky, Soumith Chintala, Léon Bottou

• Improved Training of Wasserstein GANs, Ishaan Gulrajani, Faruk Ahmed, Martin Arjovsky, Vincent Dumoulin, Aaron Courville

• Dynamic Few-shot Visual Learning without Forgetting, Spyros Gidaris, Nikos Komodakis

• A Structured Self-attentive Sentence Embedding, Zhouhan Lin, Minwei Feng, Cicero Nogueira dos Santos, Mo Yu, Bing Xiang, Bowen Zhou, Yoshua Bengio

• Nueral Machine Translation by Jointly Learning to Align and Translate, Dzmitry Bahdanau, KyungHyun Cho, Yoshua Bengio∗

• Convolutional Neural Networks for Sentence Classification, Yoon Kim

• Dynamic Routing Between Capsules, Sara Sabour, Nicholas Frosst, Geoffrey E Hinton

• A simple neural network module for relational reasoning, Adam Santoro, David Raposo, David G.T. Barrett, Mateusz Malinowski, Razvan Pascanu, Peter Battaglia, Timothy Lillicrap

• Self-Attention with Relative Position Representations, Self-Attention with Relative Position Representations Peter Shaw, Jakob Uszkoreit, Ashish Vaswani

• Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization, Ramprasaath R. Selvaraju, Michael Cogswell, Abhishek Das, Ramakrishna Vedantam, Devi Parikh, Dhruv Batra

• Distilling a Neural Network Into a Soft Decision Tree, Nicholas Frosst, Geoffrey Hinton

Read roughly

• A Simple Neural Attentive Meta-Learner, Nikhil Mishra, Mostafa Rohaninejad, Xi Chen, Pieter Abbeel

• A Unified Approach to Interpreting Model Predictions, Scott Lundberg, Su-In Lee

• VQA: Visual Question Answering, Aishwarya Agrawal, Jiasen Lu, Stanislaw Antol, Margaret Mitchell, C. Lawrence Zitnick, Dhruv Batra, Devi Parikh

• Algorithms for Hyper-Parameter Optimization, James Bergstra, Remi Bardenet, Yoshua Bengio , Balazs Kegl

Helpful resources

• WGAN: https://lilianweng.github.io/lil-log/2017/08/20/from-GAN-to-WGAN.html#hard-to-achieve-nash-equilibrium

• Kantorvich-Rubinsetin duality: https://vincentherrmann.github.io/blog/wasserstein/