2018-02

• The Matrix Calculus You Need For Deep Learning [arXiv]
• Regularized Evolution for Image Classifier Architecture Search [arXiv]
• Online Learning: A Comprehensive Survey [arXiv]
• Visual Interpretability for Deep Learning: a Survey [arXiv]
• Behavior is Everything – Towards Representing Concepts with Sensorimotor Contingencies [paper] [article] [code]
• IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures [arXiv] [article] [code]
• DeepType: Multilingual Entity Linking by Neural Type System Evolution [arXiv] [article] [code]
• DensePose: Dense Human Pose Estimation In The Wild [arXiv] [article]

2018-01

• Nested LSTMs [arXiv]
• Generating Wikipedia by Summarizing Long Sequences [arXiv]
• Scalable and accurate deep learning for electronic health records [arXiv]
• Kernel Feature Selection via Conditional Covariance Minimization [NIPS paper] [article] [code]
• Psychlab: A Psychology Laboratory for Deep Reinforcement Learning Agents [arXiv] [article] [code]
• Fine-tuned Language Models for Text Classification [arXiv] [code] (soon)
• Deep Learning: An Introduction for Applied Mathematicians [arXiv]
• Innateness, AlphaZero, and Artificial Intelligence [arXiv]
• Can Computers Create Art? [arXiv]
• eCommerceGAN : A Generative Adversarial Network for E-commerce [arXiv]
• Expected Policy Gradients for Reinforcement Learning [arXiv]
• DroNet: Learning to Fly by Driving [UZH docs] [article] [code]
• Symmetric Decomposition of Asymmetric Games [Scientific Reports] [article]
• Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor [arXiv] [code]
• SBNet: Sparse Blocks Network for Fast Inference [arXiv] [article] [code]
• DeepMind Control Suite [arXiv] [code]
• Deep Learning: A Critical Appraisal [arXiv]

2017-12

• Adversarial Patch [arXiv]
• CNN Is All You Need [arXiv]
• Learning Robot Objectives from Physical Human Interaction [paper] [article]
• The NarrativeQA Reading Comprehension Challenge [arXiv] [dataset]
• Objects that Sound [arXiv]
• Natural TTS Synthesis by Conditioning WaveNet on Mel Spectrogram Predictions [arXiv] [article] [article2]
• Deep Neuroevolution: Genetic Algorithms Are a Competitive Alternative for Training Deep Neural Networks for Reinforcement Learning [arXiv] [article] [code]
• Improving Exploration in Evolution Strategies for Deep Reinforcement Learning via a Population of Novelty-Seeking Agents [arXiv] [article] [code]
• Superhuman AI for heads-up no-limit poker: Libratus beats top professionals [Science]
• Mathematics of Deep Learning [arXiv]
• State-of-the-art Speech Recognition With Sequence-to-Sequence Models [arXiv] [article]
• Peephole: Predicting Network Performance Before Training [arXiv]
• Deliberation Network: Pushing the frontiers of neural machine translation [Research at Microsoft] [article]
• GPU Kernels for Block-Sparse Weights [Research at OpenAI] [article] [code]
• Mastering Chess and Shogi by Self-Play with a General Reinforcement Learning Algorithm [arXiv]
• Deep Learning Scaling is Predictable, Empirically [arXiv] [article]

2017-11

• High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANs [arXiv] [article] [code]
• StarGAN: Unified Generative Adversarial Networks for Multi-Domain Image-to-Image Translation [arXiv] [code]
• Population Based Training of Neural Networks [arXiv] [article]
• Distilling a Neural Network Into a Soft Decision Tree [arXiv]
• Neural Text Generation: A Practical Guide [arXiv]
• Parallel WaveNet: Fast High-Fidelity Speech Synthesis [DeepMind documents] [article]
• CheXNet: Radiologist-Level Pneumonia Detection on Chest X-Rays with Deep Learning [arXiv] [article]
• Non-local Neural Networks [arXiv]
• Deep Image Prior [paper] [article] [code]
• Online Deep Learning: Learning Deep Neural Networks on the Fly [arXiv]
• Learning Explanatory Rules from Noisy Data [arXiv]
• Improving Palliative Care with Deep Learning [arXiv] [article]
• VoxelNet: End-to-End Learning for Point Cloud Based 3D Object Detection [arXiv]
• Weighted Transformer Network for Machine Translation [arXiv] [article]
• Non-Autoregressive Neural Machine Translation [arXiv] [article]
• Block-Sparse Recurrent Neural Networks [arXiv]
• A Unified Game-Theoretic Approach to Multiagent Reinforcement Learning [arXiv]
• Neural Discrete Representation Learning [arXiv] [article]
• Don't Decay the Learning Rate, Increase the Batch Size [arXiv]
• Hierarchical Representations for Efficient Architecture Search [arXiv]

2017-10

• Unsupervised Machine Translation Using Monolingual Corpora Only [arXiv]
• Dynamic Routing Between Capsules [arXiv]
• A generative vision model that trains with high data efficiency and breaks text-based CAPTCHAs [Science] [article] [code]
• Understanding Grounded Language Learning Agents [arXiv]
• Planning, Fast and Slow: A Framework for Adaptive Real-Time Safe Trajectory Planning [arXiv] [article] [code] (soon)
• Malware Detection by Eating a Whole EXE [arXiv] [article]
• Progressive Growing of GANs for Improved Quality, Stability, and Variation [Research at Nvidia] [article] [code]
• Meta Learning Shared Hierarchies [arXiv] [article] [code]
• Deep Voice 3: 2000-Speaker Neural Text-to-Speech [arXiv] [article]
• AVA: A Video Dataset of Spatio-temporally Localized Atomic Visual Actions [arXiv] [article] [dataset]
• Mastering the game of Go without Human Knowledge [Nature] [article]
• Sim-to-Real Transfer of Robotic Control with Dynamics Randomization [arXiv] [article]
• Asymmetric Actor Critic for Image-Based Robot Learning [arXiv] [article]
• A systematic study of the class imbalance problem in convolutional neural networks [arXiv]
• Generalization in Deep Learning [arXiv]
• Swish: a Self-Gated Activation Function [arXiv]
• Emergent Translation in Multi-Agent Communication [arXiv]
• SLING: A framework for frame semantic parsing [arXiv] [article] [code]
• Meta-Learning for Wrestling [arXiv] [article] [code]
• Mixed Precision Training [arXiv] [article] [article2] [code/docs]
• Generative Adversarial Networks: An Overview [arXiv]
• Emergent Complexity via Multi-Agent Competition [arXiv] [article] [code]
• Deep Lattice Networks and Partial Monotonic Functions [Research at Google] [article] [code]
• The IIT Bombay English-Hindi Parallel Corpus [arXiv] [article]
• Rainbow: Combining Improvements in Deep Reinforcement Learning [arXiv]
• Lifelong Learning With Dynamically Expandable Networks [arXiv]
• Variational Inference & Deep Learning: A New Synthesis (Thesis) [dropbox]
• Neural Task Programming: Learning to Generalize Across Hierarchical Tasks [arXiv]
• Neural Color Transfer between Images [arXiv]
• The hippocampus as a predictive map [biorXiv] [article]
• Scalable and accurate deep learning for electronic health records [arXiv]

2017-09

• Variational Memory Addressing in Generative Models [arXiv]
• Overcoming Exploration in Reinforcement Learning with Demonstrations [arXiv]
• A Hybrid DSP/Deep Learning Approach to Real-Time Full-Band Speech Enhancement [arXiv] [article] [code]
• ChestX-ray8: Hospital-scale Chest X-ray Database and Benchmarks on Weakly-Supervised Classification and Localization of Common Thorax Diseases [CVF] [article] [dataset]
• NIMA: Neural Image Assessment [arXiv] [article]
• Generating Sentences by Editing Prototypes [arXiv] [code]
• The Consciousness Prior [arXiv]
• StarSpace: Embed All The Things! [arXiv] [code]
• Neural Optimizer Search with Reinforcement Learning [arXiv]
• Dynamic Evaluation of Neural Sequence Models [arXiv]
• Neural Machine Translation [arXiv]
• Matterport3D: Learning from RGB-D Data in Indoor Environments [arXiv] [article] [article2] [code]
• Deep Reinforcement Learning that Matters [arXiv] [code]
• The Uncertainty Bellman Equation and Exploration [arXiv]
• WESPE: Weakly Supervised Photo Enhancer for Digital Cameras [arXiv] [article]
• Globally Normalized Reader [arXiv] [article] [code]
• A Brief Introduction to Machine Learning for Engineers [arXiv]
• Learning with Opponent-Learning Awareness [arXiv] [article]
• A Deep Reinforcement Learning Chatbot [arXiv]
• Squeeze-and-Excitation Networks [arXiv]
• Efficient Methods and Hardware for Deep Learning (Thesis) [Stanford Digital Repository]

2017-08

• Design and Analysis of the NIPS 2016 Review Process [arXiv]
• Fast Automated Analysis of Strong Gravitational Lenses with Convolutional Neural Networks [arXiv] [article]
• TensorFlow Agents: Efficient Batched Reinforcement Learning in TensorFlow [white paper] [code]
• Automated Crowdturfing Attacks and Defenses in Online Review Systems [arXiv]
• Neural Network Dynamics for Model-Based Deep Reinforcement Learning with Model-Free Fine-Tuning [arXiv] [article] [code]
• Deep Learning for Video Game Playing [arXiv]
• Deep & Cross Network for Ad Click Predictions [arXiv]
• Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms [arXiv] [code]
• Multi-task Self-Supervised Visual Learning [arXiv]
• Learning a Multi-View Stereo Machine [arXiv] [article] [code] (soon)
• Twin Networks: Using the Future as a Regularizer [arXiv]
• A Brief Survey of Deep Reinforcement Learning [arXiv]
• Scalable trust-region method for deep reinforcement learning using Kronecker-factored approximation [arXiv] [code]
• On the Effectiveness of Visible Watermarks [CVPR] [article]
• Practical Network Blocks Design with Q-Learning [arXiv]
• On Ensuring that Intelligent Machines Are Well-Behaved [arXiv]
• Reproducibility of Benchmarked Deep Reinforcement Learning Tasks for Continuous Control [arXiv] [code]
• Training Deep AutoEncoders for Collaborative Filtering [arXiv] [code]
• Learning to Perform a Perched Landing on the GroundUsing Deep Reinforcement Learning [nature]
• Revisiting the Effectiveness of Off-the-shelf Temporal Modeling Approaches for Large-scale Video Classification [arXiv] [article]
• Intrinsically Motivated Goal Exploration Processes with Automatic Curriculum Learning [arXiv]
• Neural Expectation Maximization [arXiv] [code]
• Google Vizier: A Service for Black-Box Optimization [Research at Google]
• STARDATA: A StarCraft AI Research Dataset [arXiv] [code]
• Using millions of emoji occurrences to learn any-domain representations for detecting sentiment, emotion and sarcasm [arXiv] [code] [article]
• Natural Language Processing with Small Feed-Forward Networks [arXiv]

2017-07

• Photographic Image Synthesis with Cascaded Refinement Networks [arXiv] [code]
• StarCraft II: A New Challenge for Reinforcement Learning [DeepMind Documents] [code] [article]
• Leveraging Demonstrations for Deep Reinforcement Learning on Robotics Problems with Sparse Rewards [arXiv]
• Reinforcement Learning with Deep Energy-Based Policies [arXiv] [article] [code]
• DARLA: Improving Zero-Shot Transfer in Reinforcement Learning [arXiv]
• Synthesizing Robust Adversarial Examples [arXiv] [article] [code] (Soon)
• Voice Synthesis for in-the-Wild Speakers via a Phonological Loop [arXiv] [code] [article]
• Eyemotion: Classifying facial expressions in VR using eye-tracking cameras [arXiv] [article]
• A Distributional Perspective on Reinforcement Learning [arXiv] [article] [video]
• On the State of the Art of Evaluation in Neural Language Models [arXiv]
• Optimizing the Latent Space of Generative Networks [arXiv]
• Neuroscience-Inspired Artificial Intelligence [Neuron] [article]
• Learning Transferable Architectures for Scalable Image Recognition [arXiv]
• Reverse Curriculum Generation for Reinforcement Learning [arXiv]
• Imagination-Augmented Agents for Deep Reinforcement Learning [arXiv] [article]
• Learning model-based planning from scratch [arXiv] [article]
• Proximal Policy Optimization Algorithms [AWSS3] [code]
• Automatic Recognition of Deceptive Facial Expressions of Emotion [arXiv]
• Distral: Robust Multitask Reinforcement Learning [arXiv]
• Creatism: A deep-learning photographer capable of creating professional work [arXiv] [article]
• SCAN: Learning Abstract Hierarchical Compositional Visual Concepts [arXiv] [article]
• Revisiting Unreasonable Effectiveness of Data in Deep Learning Era [arXiv] [article]
• The Intentional Unintentional Agent: Learning to Solve Many Continuous Control Tasks Simultaneously [arXiv]
• Deep Bilateral Learning for Real-Time Image Enhancement [arXiv] [code] [article]
• Emergence of Locomotion Behaviours in Rich Environments [arXiv] [article]
• Learning human behaviors from motion capture by adversarial imitation [arXiv] [article]
• Robust Imitation of Diverse Behaviors [arXiv] [article]
• Hindsight Experience Replay [arXiv]
• Cardiologist-Level Arrhythmia Detection with Convolutional Neural Networks [arXiv] [article]
• End-to-End Learning of Semantic Grasping [arXiv]
• ELF: An Extensive, Lightweight and Flexible Research Platform for Real-time Strategy Games [arXiv] [code] [article]

2017-06

• Noisy Networks for Exploration [arXiv]
• Do GANs actually learn the distribution? An empirical study [arXiv]
• Gradient Episodic Memory for Continuum Learning [arXiv]
• Natural Language Does Not Emerge 'Naturally' in Multi-Agent Dialog [arXiv] [code]
• Deep Interest Network for Click-Through Rate Prediction [arXiv]
• Cognitive Psychology for Deep Neural Networks: A Shape Bias Case Study [arXiv] [article]
• Structure Learning in Motor Control: A Deep Reinforcement Learning Model [arXiv]
• Programmable Agents [arXiv]
• Grounded Language Learning in a Simulated 3D World [arXiv]
• Schema Networks: Zero-shot Transfer with a Generative Causal Model of Intuitive Physics [arXiv]
• SVCCA: Singular Vector Canonical Correlation Analysis for Deep Learning Dynamics and Interpretability [arXiv] [article] [code]
• One Model To Learn Them All [arXiv] [code] [article]
• Hybrid Reward Architecture for Reinforcement Learning [arXiv]
• Expected Policy Gradients [arXiv]
• Variational Approaches for Auto-Encoding Generative Adversarial Networks [arXiv]
• Deal or No Deal? End-to-End Learning for Negotiation Dialogues [S3AWS] [code] [article]
• Attention Is All You Need [arXiv] [code] [article]
• Sobolev Training for Neural Networks [arXiv]
• YellowFin and the Art of Momentum Tuning [arXiv] [code] [article]
• Forward Thinking: Building and Training Neural Networks One Layer at a Time [arXiv]
• Depthwise Separable Convolutions for Neural Machine Translation [arXiv] [code]
• Parameter Space Noise for Exploration [arXiv] [code] [article]
• Deep Reinforcement Learning from human preferences [arXiv] [article]
• Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments [arXiv] [code]
• Self-Normalizing Neural Networks [arXiv] [code]
• Accurate, Large Minibatch SGD: Training ImageNet in 1 Hour [arXiv]
• A simple neural network module for relational reasoning [arXiv] [article]
• Visual Interaction Networks [arXiv] [article]

2017-05

• Supervised Learning of Universal Sentence Representations from Natural Language Inference Data [arXiv] [code]
• pix2code: Generating Code from a Graphical User Interface Screenshot [arXiv] [article] [code]
• The Cramer Distance as a Solution to Biased Wasserstein Gradients [arXiv]
• Reinforcement Learning with a Corrupted Reward Channel [arXiv]
• Dilated Residual Networks [arXiv] [code]
• Bayesian GAN [arXiv] [code]
• Gradient Descent Can Take Exponential Time to Escape Saddle Points [arXiv] [article]
• Thinking Fast and Slow with Deep Learning and Tree Search [arXiv]
• ParlAI: A Dialog Research Software Platform [arXiv] [code] [article]
• Semantically Decomposing the Latent Spaces of Generative Adversarial Networks [arXiv] [article]
• Look, Listen and Learn [arXiv]
• Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset [arXiv] [code]
• Convolutional Sequence to Sequence Learning [arXiv] [code] [code2] [article]
• The Kinetics Human Action Video Dataset [arXiv] [article]
• Safe and Nested Subgame Solving for Imperfect-Information Games [arXiv]
• Discrete Sequential Prediction of Continuous Actions for Deep RL [arXiv]
• Metacontrol for Adaptive Imagination-Based Optimization [arXiv]
• Efficient Parallel Methods for Deep Reinforcement Learning [arXiv]
• Real-Time Adaptive Image Compression [arXiv]

2017-04

• General Video Game AI: Learning from Screen Capture [arXiv]
• Learning to Skim Text [arXiv]
• Get To The Point: Summarization with Pointer-Generator Networks [arXiv] [code] [article]
• Adversarial Neural Machine Translation [arXiv]
• Deep Q-learning from Demonstrations [arXiv]
• Learning from Demonstrations for Real World Reinforcement Learning [arXiv]
• DSLR-Quality Photos on Mobile Devices with Deep Convolutional Networks [arXiv] [article] [code]
• A Neural Representation of Sketch Drawings [arXiv] [code] [article]
• Automated Curriculum Learning for Neural Networks [arXiv]
• Hierarchical Surface Prediction for 3D Object Reconstruction [arXiv] [article]
• Neural Message Passing for Quantum Chemistry [arXiv]
• Learning to Generate Reviews and Discovering Sentiment [arXiv] [code]
• Best Practices for Applying Deep Learning to Novel Applications [arXiv]

2017-03

• Improved Training of Wasserstein GANs [arXiv]
• Evolution Strategies as a Scalable Alternative to Reinforcement Learning [arXiv]
• Controllable Text Generation [arXiv]
• Neural Episodic Control [arXiv]
• A Structured Self-attentive Sentence Embedding [arXiv]
• Multi-step Reinforcement Learning: A Unifying Algorithm [arXiv]
• Deep learning with convolutional neural networks for brain mapping and decoding of movement-related information from the human EEG [arXiv]
• FaSTrack: a Modular Framework for Fast and Guaranteed Safe Motion Planning [arXiv] [article] [article2]
• Massive Exploration of Neural Machine Translation Architectures [arXiv] [code]
• Large Pose 3D Face Reconstruction from a Single Image via Direct Volumetric CNN Regression [arXiv] [article] [code]
• Minimax Regret Bounds for Reinforcement Learning [arXiv]
• Sharp Minima Can Generalize For Deep Nets [arXiv]
• Parallel Multiscale Autoregressive Density Estimation [arXiv]
• Neural Machine Translation and Sequence-to-sequence Models: A Tutorial [arXiv]
• Large-Scale Evolution of Image Classifiers [arXiv]
• FeUdal Networks for Hierarchical Reinforcement Learning [arXiv]
• Evolving Deep Neural Networks [arXiv]
• How to Escape Saddle Points Efficiently [arXiv] [article]
• Opening the Black Box of Deep Neural Networks via Information [arXiv] [video]
• Understanding Synthetic Gradients and Decoupled Neural Interfaces [arXiv]
• Learning to Optimize Neural Nets [arXiv] [article]

2017-02

• The Shattered Gradients Problem: If resnets are the answer, then what is the question? [arXiv]
• Neural Map: Structured Memory for Deep Reinforcement Learning [arXiv]
• Bridging the Gap Between Value and Policy Based Reinforcement Learning [arXiv]
• Deep Voice: Real-time Neural Text-to-Speech [arXiv]
• Beating the World's Best at Super Smash Bros. with Deep Reinforcement Learning [arXiv]
• The Game Imitation: Deep Supervised Convolutional Networks for Quick Video Game AI [arXiv]
• Learning to Parse and Translate Improves Neural Machine Translation [arXiv]
• All-but-the-Top: Simple and Effective Postprocessing for Word Representations [arXiv]
• Deep Learning with Dynamic Computation Graphs [arXiv]
• Skip Connections as Effective Symmetry-Breaking [arXiv]
• odelSemi-Supervised QA with Generative Domain-Adaptive Nets [arXiv]

2017-01

• Wasserstein GAN [arXiv]
• Deep Reinforcement Learning: An Overview [arXiv]
• DyNet: The Dynamic Neural Network Toolkit [arXiv]
• DeepStack: Expert-Level Artificial Intelligence in No-Limit Poker [arXiv]
• NIPS 2016 Tutorial: Generative Adversarial Networks [arXiv]

2016-12

• A recurrent neural network without Chaos [arXiv]
• Language Modeling with Gated Convolutional Networks [arXiv]
• EnhanceNet: Single Image Super-Resolution Through Automated Texture Synthesis [arXiv] [article]
• Learning from Simulated and Unsupervised Images through Adversarial Training [arXiv]
• How Grammatical is Character-level Neural Machine Translation? Assessing MT Quality with Contrastive Translation Pairs [arXiv]
• Improving Neural Language Models with a Continuous Cache [arXiv]
• DeepMind Lab [arXiv] [code]
• Deep Learning of Robotic Tasks without a Simulator using Strong and Weak Human Supervision [arXiv]
• Knowing When to Look: Adaptive Attention via A Visual Sentinel for Image Captioning [arXiv]
• Overcoming catastrophic forgetting in neural networks [arXiv]

2016-11 (ICLR Edition)

• Image-to-Image Translation with Conditional Adversarial Networks [arXiv]
• Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer [OpenReview]
• Learning to reinforcement learn [arXiv]
• A Way out of the Odyssey: Analyzing and Combining Recent Insights for LSTMs [arXiv]
• Adversarial Training Methods for Semi-Supervised Text Classification [arXiv]
• Importance Sampling with Unequal Support [arXiv]
• Quasi-Recurrent Neural Networks [arXiv]
• Capacity and Learnability in Recurrent Neural Networks [OpenReview]
• Unrolled Generative Adversarial Networks [OpenReview]
• Deep Information Propagation [OpenReview]
• Structured Attention Networks [OpenReview]
• Incremental Sequence Learning [arXiv]
• Delving into Transferable Adversarial Examples and Black-box Attacks [arXiv] [code]
• b-GAN: Unified Framework of Generative Adversarial Networks [OpenReview]
• A Joint Many-Task Model: Growing a Neural Network for Multiple NLP Tasks [OpenReview]
• Categorical Reparameterization with Gumbel-Softmax [arXiv]
• Lip Reading Sentences in the Wild [arXiv]

Reinforcement Learning:

-Learning to reinforcement learn [arXiv]

• A Connection between Generative Adversarial Networks, Inverse Reinforcement Learning, and Energy-Based Models [arXiv]
• The Predictron: End-To-End Learning and Planning [OpenReview]
• Third-Person Imitation Learning [OpenReview]
• Generalizing Skills with Semi-Supervised Reinforcement Learning [OpenReview]
• Sample Efficient Actor-Critic with Experience Replay [OpenReview]
• Reinforcement Learning with Unsupervised Auxiliary Tasks [arXiv]
• Neural Architecture Search with Reinforcement Learning [OpenReview]
• Towards Information-Seeking Agents [OpenReview]
• Multi-Agent Cooperation and the Emergence of (Natural) Language [OpenReview]
• Improving Policy Gradient by Exploring Under-appreciated Rewards [OpenReview]
• Stochastic Neural Networks for Hierarchical Reinforcement Learning [OpenReview]
• Tuning Recurrent Neural Networks with Reinforcement Learning [OpenReview]
• RL^2: Fast Reinforcement Learning via Slow Reinforcement Learning [arXiv]
• Learning Invariant Feature Spaces to Transfer Skills with Reinforcement Learning [OpenReview]
• Learning to Perform Physics Experiments via Deep Reinforcement Learning [OpenReview]
• Reinforcement Learning through Asynchronous Advantage Actor-Critic on a GPU [OpenReview]
• Learning to Compose Words into Sentences with Reinforcement Learning[OpenReview]
• Deep Reinforcement Learning for Accelerating the Convergence Rate [OpenReview]
• #Exploration: A Study of Count-Based Exploration for Deep Reinforcement Learning [arXiv]
• Learning to Compose Words into Sentences with Reinforcement Learning [OpenReview]
• Learning to Navigate in Complex Environments [arXiv]
• Unsupervised Perceptual Rewards for Imitation Learning [OpenReview]
• Q-Prop: Sample-Efficient Policy Gradient with An Off-Policy Critic [OpenReview]

Machine Translation & Dialog

• Google's Multilingual Neural Machine Translation System: Enabling Zero-Shot Translation [arXiv]
• Neural Machine Translation with Reconstruction [arXiv]
• Iterative Refinement for Machine Translation [OpenReview]
• A Convolutional Encoder Model for Neural Machine Translation [arXiv]
• Improving Neural Language Models with a Continuous Cache [OpenReview]
• Vocabulary Selection Strategies for Neural Machine Translation [OpenReview]
• Towards an automatic Turing test: Learning to evaluate dialogue responses [OpenReview]
• Dialogue Learning With Human-in-the-Loop [OpenReview]
• Batch Policy Gradient Methods for Improving Neural Conversation Models [OpenReview]
• Learning through Dialogue Interactions [OpenReview]
• Dual Learning for Machine Translation [arXiv]
• Unsupervised Pretraining for Sequence to Sequence Learning [arXiv]

2016-10

• Hybrid computing using a neural network with dynamic external memory [nature] [code]
• Quantum Machine Learning [arXiv]
• Understanding deep learning requires rethinking generalization [arXiv]
• Universal adversarial perturbations [arXiv] [code]
• Neural Machine Translation in Linear Time [arXiv] [code]
• Professor Forcing: A New Algorithm for Training Recurrent Networks [arXiv]
• Learning to Protect Communications with Adversarial Neural Cryptography [arXiv]
• Can Active Memory Replace Attention? [arXiv]
• Using Fast Weights to Attend to the Recent Past [arXiv]
• Fully Character-Level Neural Machine Translation without Explicit Segmentation [arXiv]
• Diverse Beam Search: Decoding Diverse Solutions from Neural Sequence Models [arXiv]
• Video Pixel Networks [arXiv]
• Connecting Generative Adversarial Networks and Actor-Critic Methods [arXiv]
• Learning to Translate in Real-time with Neural Machine Translation [arXiv]
• Xception: Deep Learning with Depthwise Separable Convolutions [arXiv]
• Collective Robot Reinforcement Learning with Distributed Asynchronous Guided Policy Search [arXiv]
• Pointer Sentinel Mixture Models [arXiv]

2016-09

• Towards Deep Symbolic Reinforcement Learning [arXiv]
• HyperNetworks [arXiv]
• Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation [arXiv]
• Safe and Efficient Off-Policy Reinforcement Learning [arXiv]
• Playing FPS Games with Deep Reinforcement Learning [arXiv]
• SeqGAN: Sequence Generative Adversarial Nets with Policy Gradient [arXiv]
• Episodic Exploration for Deep Deterministic Policies: An Application to StarCraft Micromanagement Tasks [arXiv]
• Energy-based Generative Adversarial Network [arXiv]
• Stealing Machine Learning Models via Prediction APIs [arXiv]
• Semi-Supervised Classification with Graph Convolutional Networks [arXiv]
• WaveNet: A Generative Model For Raw Audio [arXiv]
• Hierarchical Multiscale Recurrent Neural Networks [arXiv]
• End-to-End Reinforcement Learning of Dialogue Agents for Information Access [arXiv]
• Deep Neural Networks for YouTube Recommendations [paper]

2016-08

• Semantics derived automatically from language corpora contain human-like biases [arXiv]
• Why does deep and cheap learning work so well? [arXiv]
• Machine Comprehension Using Match-LSTM and Answer Pointer [arXiv]
• Stacked Approximated Regression Machine: A Simple Deep Learning Approach [arXiv]
• Decoupled Neural Interfaces using Synthetic Gradients [arXiv]
• WikiReading: A Novel Large-scale Language Understanding Task over Wikipedia [arXiv]
• Temporal Attention Model for Neural Machine Translation [arXiv]
• Residual Networks of Residual Networks: Multilevel Residual Networks [arXiv]
• Learning Online Alignments with Continuous Rewards Policy Gradient [arXiv]

2016-07

• An Actor-Critic Algorithm for Sequence Prediction [arXiv]
• Cognitive Science in the era of Artificial Intelligence: A roadmap for reverse-engineering the infant language-learner [arXiv]
• Recurrent Neural Machine Translation [arXiv]
• MS-Celeb-1M: A Dataset and Benchmark for Large-Scale Face Recognition [arXiv]
• Layer Normalization [arXiv]
• Neural Machine Translation with Recurrent Attention Modeling [arXiv]
• Neural Semantic Encoders [arXiv]
• Attention-over-Attention Neural Networks for Reading Comprehension [arXiv]
• sk_p: a neural program corrector for MOOCs [arXiv]
• Recurrent Highway Networks [arXiv]
• Bag of Tricks for Efficient Text Classification [arXiv]
• Context-Dependent Word Representation for Neural Machine Translation [arXiv]
• Dynamic Neural Turing Machine with Soft and Hard Addressing Schemes [arXiv]

2016-06

• Sequence-to-Sequence Learning as Beam-Search Optimization [arXiv]
• Sequence-Level Knowledge Distillation [arXiv]
• Policy Networks with Two-Stage Training for Dialogue Systems [arXiv]
• Towards an integration of deep learning and neuroscience [arXiv]
• On Multiplicative Integration with Recurrent Neural Networks [arxiv]
• Wide & Deep Learning for Recommender Systems [arXiv]
• Online and Offline Handwritten Chinese Character Recognition [arXiv]
• Tutorial on Variational Autoencoders [arXiv]
• Concrete Problems in AI Safety [arXiv]
• Deep Reinforcement Learning Discovers Internal Models [arXiv]
• SQuAD: 100,000+ Questions for Machine Comprehension of Text [arXiv]
• Conditional Image Generation with PixelCNN Decoders [arXiv]
• Model-Free Episodic Control [arXiv]
• Progressive Neural Networks [arXiv]
• Improved Techniques for Training GANs [arXiv] [code]
• Memory-Efficient Backpropagation Through Time [arXiv]
• InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Nets [arXiv]
• Zero-Resource Translation with Multi-Lingual Neural Machine Translation [arXiv]
• Key-Value Memory Networks for Directly Reading Documents [arXiv]
• Deep Recurrent Models with Fast-Forward Connections for Neural Machine Translatin [arXiv]
• Learning to learn by gradient descent by gradient descent [arXiv]
• Learning Language Games through Interaction [arXiv]
• Zoneout: Regularizing RNNs by Randomly Preserving Hidden Activations [arXiv]
• Smart Reply: Automated Response Suggestion for Email [arXiv]
• Virtual Adversarial Training for Semi-Supervised Text Classification [arXiv]
• Deep Reinforcement Learning for Dialogue Generation [arXiv]
• Very Deep Convolutional Networks for Natural Language Processing [arXiv]
• Neural Net Models for Open-Domain Discourse Coherence [arXiv]
• Neural Architectures for Fine-grained Entity Type Classification [arXiv]
• Matching Networks for One Shot Learning [arXiv]
• Cooperative Inverse Reinforcement Learning [arXiv] [article]
• Gated-Attention Readers for Text Comprehension [arXiv]
• End-to-end LSTM-based dialog control optimized with supervised and reinforcement learning [arXiv]
• Iterative Alternating Neural Attention for Machine Reading [arXiv]
• Memory-enhanced Decoder for Neural Machine Translation [arXiv]
• Multiresolution Recurrent Neural Networks: An Application to Dialogue Response Generation [arXiv]
• Learning to Optimize [arXiv] [article]
• Natural Language Comprehension with the EpiReader [arXiv]
• Conversational Contextual Cues: The Case of Personalization and History for Response Ranking [arXiv]
• Adversarially Learned Inference [arXiv]
• OpenAI Gym [arXiv] [code]
• Neural Network Translation Models for Grammatical Error Correction [arXiv]

2016-05

• Hierarchical Memory Networks [arXiv]
• Deep API Learning [arXiv]
• Wide Residual Networks [arXiv]
• TensorFlow: A system for large-scale machine learning [arXiv]
• Learning Natural Language Inference using Bidirectional LSTM model and Inner-Attention [arXiv]
• Aspect Level Sentiment Classification with Deep Memory Network [arXiv]
• FractalNet: Ultra-Deep Neural Networks without Residuals [arXiv]
• Learning End-to-End Goal-Oriented Dialog [arXiv]
• One-shot Learning with Memory-Augmented Neural Networks [arXiv]
• Deep Learning without Poor Local Minima [arXiv]
• AVEC 2016 - Depression, Mood, and Emotion Recognition Workshop and Challenge [arXiv]
• Data Programming: Creating Large Training Sets, Quickly [arXiv]
• Deeply-Fused Nets [arXiv]
• Deep Portfolio Theory [arXiv]
• Unsupervised Learning for Physical Interaction through Video Prediction [arXiv]
• Movie Description [arXiv]

2016-04

• Higher Order Recurrent Neural Networks [arXiv]
• Joint Line Segmentation and Transcription for End-to-End Handwritten Paragraph Recognition [arXiv]
• Hierarchical Deep Reinforcement Learning: Integrating Temporal Abstraction and Intrinsic Motivation [arXiv]
• The IBM 2016 English Conversational Telephone Speech Recognition System [arXiv]
• Dialog-based Language Learning [arXiv]
• Multilingual Part-of-Speech Tagging with Bidirectional Long Short-Term Memory Models and Auxiliary Loss [arXiv]
• Sentence-Level Grammatical Error Identification as Sequence-to-Sequence Correction [arXiv]
• A Network-based End-to-End Trainable Task-oriented Dialogue System [arXiv]
• Visual Storytelling [arXiv]
• Improving the Robustness of Deep Neural Networks via Stability Training [arXiv]
• Bridging the Gaps Between Residual Learning, Recurrent Neural Networks and Visual Cortex [arXiv]
• Scan, Attend and Read: End-to-End Handwritten Paragraph Recognition with MDLSTM Attention [arXiv]
• Sentence Level Recurrent Topic Model: Letting Topics Speak for Themselves [arXiv]
• Achieving Open Vocabulary Neural Machine Translation with Hybrid Word-Character Models [arXiv]
• Building Machines That Learn and Think Like People [arXiv]
• A Semisupervised Approach for Language Identification based on Ladder Networks [arXiv]
• Deep Networks with Stochastic Depth [arXiv]
• PHOCNet: A Deep Convolutional Neural Network for Word Spotting in Handwritten Documents [arXiv]

2016-03

• Improving Information Extraction by Acquiring External Evidence with Reinforcement Learning [arXiv]
• A Fast Unified Model for Parsing and Sentence Understanding [arXiv]
• Latent Predictor Networks for Code Generation [arXiv]
• Attend, Infer, Repeat: Fast Scene Understanding with Generative Models [arXiv]
• Recurrent Batch Normalization [arXiv]
• Neural Language Correction with Character-Based Attention [arXiv]
• Incorporating Copying Mechanism in Sequence-to-Sequence Learning [arXiv]
• How NOT To Evaluate Your Dialogue System [arXiv]
• Adaptive Computation Time for Recurrent Neural Networks [arXiv]
• A guide to convolution arithmetic for deep learning [arXiv]
• Colorful Image Colorization [arXiv]
• Unsupervised Learning of Visual Representations by Solving Jigsaw Puzzles [arXiv]
• Generating Factoid Questions With Recurrent Neural Networks: The 30M Factoid Question-Answer Corpus [arXiv]
• A Persona-Based Neural Conversation Model [arXiv]
• A Character-level Decoder without Explicit Segmentation for Neural Machine Translation [arXiv]
• Multi-Task Cross-Lingual Sequence Tagging from Scratch [arXiv]
• Neural Variational Inference for Text Processing [arXiv]
• Recurrent Dropout without Memory Loss [arXiv]
• One-Shot Generalization in Deep Generative Models [arXiv]
• Recursive Recurrent Nets with Attention Modeling for OCR in the Wild [[arXiv](Recursive Recurrent Nets with Attention Modeling for OCR in the Wild)]
• A New Method to Visualize Deep Neural Networks [[arXiv](A New Method to Visualize Deep Neural Networks)]
• Neural Architectures for Named Entity Recognition [arXiv]
• End-to-end Sequence Labeling via Bi-directional LSTM-CNNs-CRF [arXiv]
• Character-based Neural Machine Translation [arXiv]
• Learning Word Segmentation Representations to Improve Named Entity Recognition for Chinese Social Media [arXiv]

2016-02

• Architectural Complexity Measures of Recurrent Neural Networks [arXiv]
• Weight Normalization: A Simple Reparameterization to Accelerate Training of Deep Neural Networks [arXiv]
• Recurrent Neural Network Grammars [arXiv]
• Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations [arXiv]
• Contextual LSTM (CLSTM) models for Large scale NLP tasks [arXiv]
• Sequence-to-Sequence RNNs for Text Summarization [arXiv]
• Extraction of Salient Sentences from Labelled Documents [arXiv]
• Learning Distributed Representations of Sentences from Unlabelled Data [arXiv]
• Benefits of depth in neural networks [arXiv]
• Associative Long Short-Term Memory [arXiv]
• Why Should I Trust You?": Explaining the Predictions of Any Classifier [arXiv] [code]
• Generating images with recurrent adversarial networks [arXiv]
• Exploring the Limits of Language Modeling [arXiv]
• Swivel: Improving Embeddings by Noticing What’s Missing [arXiv]
• WebNav: A New Large-Scale Task for Natural Language based Sequential Decision Making [arXiv]
• Efficient Character-level Document Classification by Combining Convolution and Recurrent Layers [arXiv]
• Gradient Descent Converges to Minimizers [arXiv] [article]
• BinaryNet: Training Deep Neural Networks with Weights and Activations Constrained to +1 or -1 [arXiv]
• Learning Discriminative Features via Label Consistent Neural Network [arXiv]

2016-01

• What’s your ML test score? A rubric for ML production systems [Research at Google]
• Pixel Recurrent Neural Networks [arXiv]
• Bitwise Neural Networks [arXiv]
• Long Short-Term Memory-Networks for Machine Reading [arXiv]
• Coverage-based Neural Machine Translation [arXiv]
• Understanding Deep Convolutional Networks [arXiv]
• Training Recurrent Neural Networks by Diffusion [arXiv]
• Automatic Description Generation from Images: A Survey of Models, Datasets, and Evaluation Measures [arXiv]
• Multi-Way, Multilingual Neural Machine Translation with a Shared Attention Mechanism [arXiv]
• Recurrent Memory Network for Language Modeling [arXiv]
• Language to Logical Form with Neural Attention [arXiv]
• Learning to Compose Neural Networks for Question Answering [arXiv]
• The Inevitability of Probability: Probabilistic Inference in Generic Neural Networks Trained with Non-Probabilistic Feedback [arXiv]
• COCO-Text: Dataset and Benchmark for Text Detection and Recognition in Natural Images [arXiv]
• Survey on the attention based RNN model and its applications in computer vision [arXiv]

2015-12

NLP

• Strategies for Training Large Vocabulary Neural Language Models [arXiv]
• Multilingual Language Processing From Bytes [arXiv]
• Learning Document Embeddings by Predicting N-grams for Sentiment Classification of Long Movie Reviews [arXiv]
• Target-Dependent Sentiment Classification with Long Short Term Memory [arXiv]
• Reading Text in the Wild with Convolutional Neural Networks [arXiv]

Vision

• Deep Residual Learning for Image Recognition [arXiv]
• Rethinking the Inception Architecture for Computer Vision [arXiv]
• Inside-Outside Net: Detecting Objects in Context with Skip Pooling and Recurrent Neural Networks [arXiv]
• Deep Speech 2: End-to-End Speech Recognition in English and Mandarin [arXiv]

2015-11

NLP

• Deep Reinforcement Learning with a Natural Language Action Space [arXiv]
• Sequence Level Training with Recurrent Neural Networks [arXiv]
• Teaching Machines to Read and Comprehend [arxiv]
• Semi-supervised Sequence Learning [arXiv]
• Multi-task Sequence to Sequence Learning [arXiv]
• Alternative structures for character-level RNNs [arXiv]
• Larger-Context Language Modeling [arXiv]
• A Unified Tagging Solution: Bidirectional LSTM Recurrent Neural Network with Word Embedding [arXiv]
• Towards Universal Paraphrastic Sentence Embeddings [arXiv]
• BlackOut: Speeding up Recurrent Neural Network Language Models With Very Large Vocabularies [arXiv]
• Sequence Level Training with Recurrent Neural Networks [arXiv]
• Natural Language Understanding with Distributed Representation [arXiv]
• sense2vec - A Fast and Accurate Method for Word Sense Disambiguation In Neural Word Embeddings [arXiv]
• LSTM-based Deep Learning Models for non-factoid answer selection [arXiv]

Programs

• Neural Random-Access Machines [arxiv]
• Neural Programmer: Inducing Latent Programs with Gradient Descent [arXiv]
• Neural Programmer-Interpreters [arXiv]
• Learning Simple Algorithms from Examples [arXiv]
• Neural GPUs Learn Algorithms [arXiv] [code]
• On Learning to Think: Algorithmic Information Theory for Novel Combinations of Reinforcement Learning Controllers and Recurrent Neural World Models [arXiv]

Vision

• ReSeg: A Recurrent Neural Network for Object Segmentation [arXiv]
• Deconstructing the Ladder Network Architecture [arXiv]
• Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks [arXiv]
• Multi-Scale Context Aggregation by Dilated Convolutions [arXiv] [code]

General

• Towards Principled Unsupervised Learning [arXiv]
• Dynamic Capacity Networks [arXiv]
• Generating Sentences from a `ous Space [arXiv]
• Net2Net: Accelerating Learning via Knowledge Transfer [arXiv]
• A Roadmap towards Machine Intelligence [arXiv]
• Session-based Recommendations with Recurrent Neural Networks [arXiv]
• Regularizing RNNs by Stabilizing Activations [arXiv]

2015-10

• A Sensitivity Analysis of (and Practitioners' Guide to) Convolutional Neural Networks for Sentence Classification [arXiv]
• Attention with Intention for a Neural Network Conversation Model [arXiv]
• Part-of-Speech Tagging with Bidirectional Long Short-Term Memory Recurrent Neural Network [arXiv]
• A Survey: Time Travel in Deep Learning Space: An Introduction to Deep Learning Models and How Deep Learning Models Evolved from the Initial Ideas [arXiv]
• A Primer on Neural Network Models for Natural Language Processing [arXiv]
• A Diversity-Promoting Objective Function for Neural Conversation Models [arXiv]

2015-09

• Character-level Convolutional Networks for Text Classification [arXiv]
• A Neural Attention Model for Abstractive Sentence Summarization [arXiv]
• Poker-CNN: A Pattern Learning Strategy for Making Draws and Bets in Poker Games [arXiv]

2015-08

• Neural Machine Translation of Rare Words with Subword Units [arXiv] [code]
• Listen, Attend and Spell [arxiv]
• Character-Aware Neural Language Models [arXiv]
• Improved Transition-Based Parsing by Modeling Characters instead of Words with LSTMs [arXiv]
• Finding Function in Form: Compositional Character Models for Open Vocabulary Word Representation [arXiv]
• Effective Approaches to Attention-based Neural Machine Translation [arXiv]

2015-07

• Building End-To-End Dialogue Systems Using Generative Hierarchical Neural Network Models [arXiv]
• Semi-Supervised Learning with Ladder Networks [arXiv]
• Document Embedding with Paragraph Vectors [arXiv]
• Training Very Deep Networks [arXiv]

2015-06

• Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning [arXiv]
• A Neural Network Approach to Context-Sensitive Generation of Conversational Responses [arXiv]
• Document Embedding with Paragraph Vectors [arXiv]
• A Neural Conversational Model [arXiv]
• Skip-Thought Vectors [arXiv]
• Pointer Networks [arXiv]
• Spatial Transformer Networks [arXiv]
• Tree-structured composition in neural networks without tree-structured architectures [arXiv]
• Visualizing and Understanding Neural Models in NLP [arXiv]
• Learning to Transduce with Unbounded Memory [arXiv]
• Ask Me Anything: Dynamic Memory Networks for Natural Language Processing [arXiv]
• Deep Knowledge Tracing [arXiv]

2015-05

• ReNet: A Recurrent Neural Network Based Alternative to Convolutional Networks [arXiv]
• Reinforcement Learning Neural Turing Machines [arXiv]

2015-04

• Correlational Neural Networks [arXiv]

2015-03

• Distilling the Knowledge in a Neural Network [arXiv]
• End-To-End Memory Networks [arXiv]
• Neural Responding Machine for Short-Text Conversation [arXiv]
• Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift [arXiv]
• Escaping From Saddle Points --- Online Stochastic Gradient for Tensor Decomposition [arXiv] [[article](Escaping from Saddle Points)]

2015-02

• Human-level control through deep reinforcement learning [Nature] [code]
• Text Understanding from Scratch [arXiv]
• Show, Attend and Tell: Neural Image Caption Generation with Visual Attention [arXiv]

2015-01

• Hidden Technical Debt in Machine Learning Systems [NIPS]

2014-12

• Learning Longer Memory in Recurrent Neural Networks [arXiv]
• Neural Turing Machines [arxiv]
• Grammar as a Foreign Langauage [arXiv]
• On Using Very Large Target Vocabulary for Neural Machine Translation [arXiv]
• Effective Use of Word Order for Text Categorization with Convolutional Neural Networks [arXiv]
• Multiple Object Recognition with Visual Attention [arXiv]

2014-11

• The Loss Surfaces of Multilayer Networks [arXiv]

2014-10

• Learning to Execute [arXiv]

2014-09

• Sequence to Sequence Learning with Neural Networks [arXiv]
• Neural Machine Translation by Jointly Learning to Align and Translate [arxiv]
• On the Properties of Neural Machine Translation: Encoder-Decoder Approaches [arXiv]
• Recurrent Neural Network Regularization [arXiv]
• Very Deep Convolutional Networks for Large-Scale Image Recognition [arXiv]
• Going Deeper with Convolutions [arXiv]

2014-08

• Convolutional Neural Networks for Sentence Classification [arxiv]

2014-07

2014-06

• Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation [arXiv]
• Recurrent Models of Visual Attention [arXiv]
• Generative Adversarial Networks [arXiv]

2014-05

• Distributed Representations of Sentences and Documents [arXiv]

2014-04

• A Convolutional Neural Network for Modelling Sentences [arXiv]

2014-03

2014-02

2014-01

• Machine Learning: The High Interest Credit Card of Technical Debt [Research at Google]

2013

• Visualizing and Understanding Convolutional Networks [arXiv]
• DeViSE: A Deep Visual-Semantic Embedding Model [pub]
• Maxout Networks [arXiv]
• Exploiting Similarities among Languages for Machine Translation [arXiv]
• Efficient Estimation of Word Representations in Vector Space [arXiv]

2011

• Natural Language Processing (almost) from Scratch [arXiv]