GokuMohandas/casual-digressions

Goku Mohandas

One Shot Learning

• Matching Networks for One Shot Learning [arXiv]

Recommendation Engines

• Deep Neural Networks for Youtube Recommendations [Google]

Representation Learning

• Doctor AI: Predicting Clinical Events via Recurrent Neural Networks [arXiv]

• Distributed Representations of Words and Phrases and their Compositionality [NIPS]

• Multi-layer Representation Learning for Medical Concepts [[arXiv] (https://arxiv.org/abs/1602.05568)]

• Poincare Embeddings for Learning Hierarchical Representations [arXiv]

• Learning to Compute Word Embeddings On the Fly [arXiv]

Text Classification

• Convolutional Neural Networks for Sentence Classification [arXiv]

• Recurrent Neural Network Regularization [arXiv]

• Grammar as a Foreign Language [arXiv]

Seq-to-Seq Models (translation)

• Sequence to Sequence Learning with Neural Networks [arXiv]

• Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation [[arXiv] (http://arxiv.org/abs/1406.1078)]

• Neural Machine Translation by Jointly Learning to Align and Translate [arXiv] - Attention in RNNs

• On Using Very Large Target Vocabulary for Neural Machine Translation [arXiv] - Sampled Softmax

• Pointer Sentinel Mixture Models [arXiv]

• Context-Dependent Word Representation for Neural Machine Translation [arXiv]

• Learning to Translate in Real-time with Neural Machine Translation [arXiv]

• Fully Character-Level Neural Machine Translation without Explicit Segmentation [arXiv]

Neural Conversation Models / QA

• A Neural Conversational Model [[arXiv] (http://arxiv.org/abs/1506.05869)]

• End-To-End Memory Networks [arXiv]

• Ask Me Anything: Dynamic Memory Networks for Natural Language Processing [arXiv]

• Dynamic Memory Networks for Visual and Textual Question Answering [arXiv]

• Dynamic Coattention Networks For Question Answering [arXiv]

• Richard Socher on the Future of Deep Learning [OReilly]

• [A Joint Many-Task Model: Growing a Neural Network for Multiple NLP Tasks][arXiv]

• Bidirectional Attention Flow for Machine Comprehension [arXiv]

• Generating Long and Diverse Responses with Neural Conversation Models [arXiv]

• Gated-Attention Readers for Text Comprehension [arXiv]

• FVQA: Fact based Visual Question Answering [arXiv]

• Query-Reduction Networks for Question Answering [arXiv]

• Question Answering through Transfer Learning from Large Fine-grained Supervision Data [arXiv]

• A Joint Many-Task Model: Growing a Neural Network for Multiple NLP Tasks [arXiv]

• Question Answering from Unstructured Text by Retrieval and Comprehension [arXiv]

Logic/Reasoning

• [Chains of Reasoning over Entities, Relations, and Text using Recurrent Neural Networks] [arXiv]

• [Deep API Learning] [arXiv]

Reinforcement Learning

• Episodic Exploration for Deep Deterministic Policies: An Application to StarCraft Micromanagement Tasks [[arXiv] (http://arxiv.org/abs/1609.02993)]

• Third Person Imitation Learning [arXiv]

Google DeepMind

• WaveNet: A Generative Model for Raw Audio [[arXiv] (https://arxiv.org/abs/1609.03499)][[Tutorial] (https://deepmind.com/blog/wavenet-generative-model-raw-audio/)]

• Decoupled Neural Interfaces using Synthetic Gradients [[arXiv] (https://arxiv.org/abs/1608.05343)] [[Tutorial] (https://deepmind.com/blog/decoupled-neural-networks-using-synthetic-gradients/)]

Neural Turing Machines

• Neural Turing Machines [[arXiv] (http://arxiv.org/abs/1410.5401)]

• [Hybrid Computing using a Neural Network with Dynamic External Memory] [Nature]

Generative Adversarial Networks

• Generative Adversarial Networks [[arXiv] (https://arxiv.org/abs/1406.2661)]

• Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks [arXiv]

• Generative Adversarial Text to Image Synthesis [[arXiv] (https://arxiv.org/abs/1605.05396)]

• Improved Techniques for Training GANs [[arXiv] (https://arxiv.org/abs/1606.03498)]

• Learning to Protect Communications with Adversarial Neural Cryptography [arXiv]

Image Captioning

• Show, Attend and Tell: Neural Image Caption Generation with Visual Attention [arXiv]

Generalization / Interpretabliity

• Understanding Deep Learning Requires Rethinking Generalization [[arXiv] (https://arxiv.org/abs/1505.00387)]

• Making Neural Programming Architecture Generalize Via Recursion [OpenReview]

• Opening the Black Box of Deep Neural Networks via Information [arXiv]

Optimization / Architecture

• Highway Networks [[arXiv] (https://arxiv.org/abs/1611.03530)]

• [Maxout Networks] [arXiv]

• HyperNetworks [[arXiv] (https://arxiv.org/abs/1609.09106)]

• [Using Fast Weights to Attend to the Recent Past] (notes/fast_weights.md) [[arXiv] (https://arxiv.org/abs/1610.06258)]

• Quasi-Recurrent Neural Networks [arXiv]

• Learning to learn by gradient descent by gradient descent [arXiv]

• GRAM: Graph-based Attention Model for Healthcare Representation Learning [arXiv]

• [Language Modeling with Gated Convolutional Networks] [arXiv]

• [Value Iteration Networks] [arXiv]

• [Adding Gradient Noise Improves Learning for Very Deep Networks] [arXiv]

• Outrageously Large Neural Networks: The Sparsely-gated Mixture-of-Experts Layer [Open Review]

• Overcoming Catastrophic Forgetting in Neural Networks [arXiv]

• Exploring Sparsity in Recurrent Neural Networks [arXiv]