2018 May

• Exploring the structure of a real-time, arbitrary neural artistic stylization network [arXiv] (Google Brain)
• Semantic Style Transfer and Turning Two-Bit Doodles into Fine Artworks [arXiv]
• Neural Style Transfer: A Review [arXiv]
• Boosting Domain Adaptation by Discovering Latent Domains [arXiv]
• Arbitrary Style Transfer with Deep Feature Reshuffle [arXiv]
• From Word to Sense Embeddings: A Survey on Vector Representations of Meaning [arXiv]
• World Models [arXiv] (Schmidhuber)
• Data science is science's second chance to get causal inference right: A classification of data science tasks [arXiv] (Hernan)
• Label Refinery: Improving ImageNet Classification through Label Progression [arXiv]
• Transferring GANs: generating images from limited data [arXiv]
• Joint 3D Face Reconstruction and Dense Alignment with Position Map Regression Network [arXiv]
• Semi-parametric Image Synthesis [arXiv]
• Revisiting Small Batch Training for Deep Neural Networks [arXiv]

2018 April

• Training Deep Networks with Synthetic Data: Bridging the Reality Gap by Domain Randomization [arXiv] (NVIDIA)
• Deep Face Recognition: A Survey [arXiv]
• Deep Probabilistic Programming Languages: A Qualitative Study [arXiv] (IBM)
• VISUALIZING THE LOSS LANDSCAPE OF NEURAL NETS [arXiv]
• PRUNING FILTERS FOR EFFICIENT CONVNETS [arXiv]
• A disciplined approach to neural network hyper-parameters: Part 1 -- learning rate, batch size, momentum, and weight decay [arXiv]
• Convolutional Neural Networks Regularized by Correlated Noise [arXiv]
• Universal Sentence Encoder [arXiv] (Google Brain, Kurzweil)
• A systematic study of the class imbalance problem in convolutional neural networks [arXiv]
• Averaging Weights Leads to Wider Optima and Better Generalization [arXiv]
• The History Began from AlexNet: A Comprehensive Survey on Deep Learning Approaches [arXiv]
• Neural Network Quine [arXiv]
• Recurrent Residual Convolutional Neural Network based on U-Net (R2U-Net) for Medical Image Segmentation [arXiv]
• Group Normalization [arXiv] (FAIR, Kaiming He)

2018 March

• DO GANS LEARN THE DISTRIBUTION? SOME THEORY AND EMPIRICS [arXiv]
• One Big Net For Everything [arXiv] (Schmidhuber)
• Diversity is All You Need: Learning Skills without a Reward Function [arXiv]
• Learning to Prune Filters in Convolutional Neural Networks [arXiv]
• Adversarial Examples that Fool both Human and Computer Vision [arXiv] (Goodfellow)
• Automatic Real-time Background Cut for Portrait Videos [arXiv]
• Pixel Objectness [arXiv]
• The Building Blocks of Interpretability [distill]

2018 Febuary

• Deep Learning Book (Approximate Inference) [Book] (Goodfellow, Bengio, Courville)
• Deep Learning Book (Confronting the Partition Function) [Book] (Goodfellow, Bengio, Courville)
• Deep Learning Book (Monte Carlo Methods) [Book] (Goodfellow, Bengio, Courville)
• Deep Learning Book (Structured Probabilistic Modelsfor Deep Learning) [Book] (Goodfellow, Bengio, Courville)
• Deep Learning Book (Representational Learning) [Book] (Goodfellow, Bengio, Courville)
• Image-to-Image Translation with Conditional Adversarial Networks [arXiv] (BAIR)
• Scalable and accurate deep learning for electronic health records [arXiv] (Google Brain)
• Generating Wikipedia by Summarizing Long Sequences [arXiv] (Google Brain)
• Visual Interpretability for Deep Learning: a Survey [[https://arxiv.org/abs/1802.00614]]
• Imitation networks: Few-shot learning of neural networks from scratch [arXiv] (Ghahramani)
• Nested LSTMs [arXiv] (Krueger)
• DensePose: Dense Human Pose Estimation In The Wild [arXiv] (FAIR)
• Regularized Evolution for Image Classifier Architecture Search [arXiv] (Quoc Le, Google Brain)
• Artificial Intelligence and Statistics [arXiv] (Bin Yu)
• Focal Loss for Dense Object Detection [arXiv] (FAIR, He)
• Stacked What-Where Auto-encoders [arXiv] (NYU, LeCun)
• Deep Learning Book (Autoencoders) [Book] (Goodfellow, Bengio, Courville)
• Transforming Auto-encoders [UT] (Hinton, Krizhevsky)
• Top-down Neural Attention by Excitation Backprop [arXiv]
• Visualizing and Understanding Convolutional Networks [NYU]
• Uncertainty-Driven 6D Pose Estimation of Objects and Scenes from a Single RGB Image [arXiv] (Dresden)
• Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks [arXiv] (BAIR)
• Sim-to-Real Robot Learning from Pixels with Progressive Nets [arXiv] (Deepmind)
• Convolutional Pose Machines [arXiv] (CMU)
• Real-Time Seamless Single Shot 6D Object Pose Prediction [arXiv]
• Beyond Word Importance: Contextual Decomposition to Extract Interactions from LSTMs [arXiv] (Google Brain)
• Large-Scale Evolution of Image Classifiers [arXiv] (Google Brain)
• Neural Program Synthesis with Priority Queue Training [arXiv] (Google Brain)
• One Model To Learn Them All [arXiv] (Google Brain)
• The Shattered Gradients Problem: If resnets are the answer, then what is the question? [arXiv]
• When Will AI Exceed Human Performance? Evidence from AI Experts [arXiv]
• Can Computers Create Art? [arXiv] (Adobe)
• Building Machines that Learn and Think for Themselves [arXiv] (Deepmind)
• Building Machines That Learn and Think Like People [arXiv] (Tenenbaum)
• Deep Learning for Sentiment Analysis : A Survey [arXiv]
• Fine-Grained Recognition without Part Annotations [stanford] (Fei Fei)

2018 January

• Deep Image Prior [arXiv] (Vedaldi, Krueger)
• Recent Advances in Recurrent Neural Networks [arXiv]
• Deep Learning: A Critical Appraisal [arXiv] (Gary Marcus)

2017 September - October

• Wasserstein GAN [arXiv]
• Cut, Paste and Learn: Surprisingly Easy Synthesis for Instance Detection [arXiv] (CMU)

2017 August

• Domain-Adversarial Training of Neural Networks [JMLR]
• Domain Separation Networks [NIPS] (Brain)
• REVISITING BATCH NORMALIZATION FOR PRACTICAL DOMAIN ADAPTATION [arXiv]
• Domain Adaptation for Visual Applications: A Comprehensive Survey [arXiv]
• Unsupervised Pixel–Level Domain Adaptation with Generative Adversarial Networks [arXiv] (Brain)
• Image Style Transfer Using Convolutional Neural Networks [IEEE]
• Generating Images with Perceptual Similarity Metrics based on Deep Networks [arXiv]
• Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network [arXiv] (Twitter)
• Photographic Image Synthesis with Cascaded Refinement Networks [Stanford]
• Kernel-Predicting Convolutional Networks for Denoising Monte Carlo Renderings [Pixar]
• Feature Pyramid Networks for Object Detection [arXiv] (FAIR)
• PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space [arXiv] (H. Su)
• PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation [arXiv] (H. Su)
• Learning from Simulated and Unsupervised Images through Adversarial Training [arXiv] (Apple)
• Pyramid Scene Parsing Network [arXiv]

2017 July

• Learning Efficient Point Cloud Generation for Dense 3D Object Reconstruction [arXiv]
• Representation Learning and Adversarial Generation of 3D Point Clouds [arXiv]
• Learning to Refine Object Segments [arXiv]
• Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning [arXiv] (Szegedy, Ioffe)
• A MultiPath Network for Object Detection [arXiv]
• Mask R-CNN [arXiv] (He)
• Fully Convolutional Instance-aware Semantic Segmentation [arXiv] (Dai)
• A Self-supervised Learning System for Object Detection using Physics Simulation and Multi-view Pose Estimation [arXiv]
• Pixelwise Instance Segmentation with a Dynamically Instantiated Network [arXiv] (Torr)
• Deep Watershed Transform for Instance Segmentation [arXiv]
• Instance-sensitive Fully Convolutional Networks [arXiv]
• Boundary-aware Instance Segmentation [arXiv]
• Speed/accuracy trade-offs for modern convolutional object detectors [arXiv] (Murphy)
• InstanceCut: from Edges to Instances with MultiCut [arXiv]
• SSD: Single Shot MultiBox Detector [arXiv] (Szegedy)
• End-to-End Instance Segmentation with Recurrent Attention [arXiv]
• Recurrent Instance Segmentation [arXiv] (Torr)
• A Review on Deep Learning Techniques Applied to Semantic Segmentation [arXiv]
• Learning to Segment Object Candidates [arXiv] (FAIR)
• PARSENET: LOOKING WIDER TO SEE BETTER [arXiv]
• A Point Set Generation Network for 3D Object Reconstruction from a Single Image [arXiv] (Su)
• 3D-R2N2: A Unified Approach for Single and Multi-view 3D Object Reconstruction [arXiv]
• FuseNet [paper]
• Multi-View Deep Learning for Consistent Semantic Mapping with RGB-D Cameras [arXiv]
• Multi-view Self-supervised Deep Learning for 6D Pose Estimation in the Amazon Picking Challenge [arXiv] (Xiao)
• Multi-view Face Detection Using Deep Convolutional Neural Networks [arXiv]
• A Comparative Analysis and Study of Multiview CNN Models for Joint Object Categorization and Pose Estimation [MLR]
• Aligning 3D Models to RGB-D Images of Cluttered Scenes [Berkeley]
• Real-Time Grasp Detection Using Convolutional Neural Networks [arXiv]
• SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size [arXiv]
• SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation [arXiv]
• You Only Look Once: Unified, Real-Time Object Detection [arXiv]
• DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs [arXiv] (Murphy)
• Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks [arXiv]
• Deep learning in neural networks: An overview [IAState] (Schmidhuber)
• A comparative study of video-based object recognition from an egocentric viewpoint [paper]
• The 2017 DAVIS Challenge on Video Object Segmentation [arXiv]
• Learning Video Object Segmentation with Visual Memory [arXiv]
• Dilated Residual Networks [arXiv] (Yu)
• Semantic Scene Completion from a Single Depth Image [arXiv] (Yu)
• Multi-view CNN (MVCNN) for shape recognition [arXiv] [Code]
• A guide to convolution arithmetic for deep learning [arXiv]
• Multi-Scale Context Aggregation by Dilated Convolutions [arXiv] (Yu)
• 3D Attention-Driven Depth Acquisition for Object Identification [Stanford] [Code]

2017 May

• Joint Embeddings of Shapes and Images via CNN Image Purification [Stanford]
• View-invariant Representations of Familiar Objects by Neurons in the Inferior Temporal Visual Cortex [Oxford]
• ONE-SHOT VIEW INVARIANCE IN A MOVING WORLD [WEXLER]
• Deep Learning Book (Applications) [Book] (Goodfellow, Bengio, Courville)
• Semi-Supervised Learning with Ladder Networks [arXiv]
• Deep Learning Book (Practical Methodology) [Book] (Goodfellow, Bengio, Courville)
• Human-level concept learning through probabilistic program induction [Science] (Tenenbaum)

2017 April

• LEARNING TO PROTECT COMMUNICATIONS WITH ADVERSARIAL NEURAL CRYPTOGRAPHY [arXiv] (Google Brian)
• NEURAL PROGRAMMER: INDUCING LATENT PROGRAMS WITH GRADIENT DESCENT [arXiv] (Quoc Le, Sutskever)
• Professor Forcing: A New Algorithm for Training Recurrent Networks [arXiv] (Courville, Bengio)
• OUTRAGEOUSLY LARGE NEURAL NETWORKS: THE SPARSELY-GATED MIXTURE-OF-EXPERTS LAYER [arXiv] (Quoc Le, Hinton, Dean)
• CATEGORICAL REPARAMETERIZATION WITH GUMBEL-SOFTMAX [arXiv] (Google Brain)
• Neural Machine Translation in Linear Time [arXiv] (Graves)
• WIKIREADING: A Novel Large-scale Language Understanding Task over Wikipedia [arXiv] (Google Research)
• Generative Adversarial Imitation Learning [arXiv] (Stanford)
• ENERGY-BASED GENERATIVE ADVERSARIAL NET- WORKS [arXiv] (LeCun)
• Transferability in Machine Learning: from Phenomena to Black-Box Attacks using Adversarial Samples [arXiv] (Goodfellow)
• HIERARCHICAL MULTISCALE RECURRENT NEURAL NETWORKS [arXiv]
• Decoupled Neural Interfaces using Synthetic Gradients [arXiv]
• Top-down Neural Attention by Excitation Backprop [arXiv]
• Generalization and Equilibrium in Generative Adversarial Nets (GANs) [arXiv]
• A Mathematical Theory of Communication [Harvard Math]
• Episodic Exploration for Deep Deterministic Policies: An Application to StarCraft Micromanagement Tasks [arXiv]
• Random feedback weights support learning in deep neural networks [arXiv]

2017 March

• Deep Learning Book (Sequence Modeling: Recurrentand Recursive Nets) [Book]
• Wide Residual Networks [arXiv]
• Identity Mappings in Deep Residual Networks [arXiv]
• Deep Residual Learning for Image Recognition [arXiv]
• DRAW: A Recurrent Neural Network For Image Generation [arXiv]
• Recurrent Models of Visual Attention [NIPS]
• MULTIPLE OBJECT RECOGNITION WITH VISUAL ATTENTION [arXiv]
• PathNet: Evolution Channels Gradient Descent in Super Neural Networks [arXiv]
• Visualizing Data using t-SNE [JMLR]
• Statistical Modeling: The Two Cultures [JSTOR]
• Understanding Neural Networks Through Deep Visualization [arXiv]
• WAVENET: A GENERATIVE MODEL FOR RAW AUDIO [arXiv]
• Attention and Augmented Recurrent Neural Networks [Distill]
• DEEP PROBABILISTIC PROGRAMMING [arXiv]
• NEURAL ARCHITECTURE SEARCH WITH REINFORCEMENT LEARNING [arXiv]
• Effective Python [Site]
• Pro Python [Site]

2017 February

• Understanding Neural Networks through Representation Erasure [arXiv]
• Shapecollage: occlusion-aware, example-based shape interpretation [MIT]
• HOW THE BRAIN MIGHT WORK: A HIERARCHICAL AND TEMPORAL MODEL FOR LEARNING AND RECOGNITION [MIT]
• Perceptual symbol systems [UCSD]
• The parallel distributed processing approach to semantic cognition [Nature]
• Unsupervised Learning of Invariant Feature Hierarchies with Applications to Object Recognition [LeCun]
• API design for machine learning software: experiences from the scikit-learn project [arXiv]
• Image-based object recognition in man, monkey and machine [Science]
• Recognition-by-Components: A Theory of Human Image Understanding [MIT]
• Graphical models and message-passing algorithms: Some introductory lectures [Berkeley]
• Hierarchical Bayesian inference in the visual cortex [CMU]
• 3-D Depth Reconstruction from a Single Still Image [Cornell]

2017 January

• Deep Learning (Convoluational NN) [MIT Press]

2016 December

• Rationalizing Neural Predictions [arXiv]
• Using “Annotator Rationales” to Improve Machine Learning for Text Categorization [JHU]

2016 September

• Why does deep and cheap learning work so well? [arXiv]

2016 August

• Deep Generative Image Models using a Laplacian Pyramid of Adversarial Networks [arXiv]
• Exploring the Limits of Language Modeling [arXiv]
• Dataset and Neural Recurrent Sequence Labeling Model for Open-Domain Factoid Question Answering [arXiv]
• Recurrent Models of Visual Attention [arXiv]
• Playing Atari with Deep Reinforcement Learning [Toronto]
• InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Nets [arXiv]
• Improved Techniques for Training GANs [arXiv]
• Neural Turing Machines [arXiv]
• Harnessing Deep Neural Networks with Logic Rules [arXiv]
• Random Search for Hyper-Parameter Optimization [JMLR]
• Going Deeper with Convolutions [CVF]
• Visualizing and Understanding Convolutional Networks [arXiv]
• Bag of Tricks for Efficient Text Classification [arXiv]
• A Thorough Examination of the CNN/Daily Mail Reading Comprehension Task [arXiv]
• Full Resolution Image Compression with Recurrent Neural Networks [arXiv]
• Neural Module Networks [arXiv]
• Deep Residual Learning for Image Recognition [arXiv]
• Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift [arXiv]
• Memory Networks [arXiv]
• Natural Language Comprehension with the EpiReader [arXiv]
• Learning to Compose Neural Networks for Question Answering [arXiv]
• LSTM: A Search Space Odyssey [arXiv]
• Deep Networks with Stochastic Depth [arXiv]
• Open AI Research #1 [Link]
• Human tests of materials for the Winograd Schema Challenge 2016 [NYU]

2016 July

• Deep Learning (Chapters up to Regularization) [MIT Press]
• You Only Die Once: Counting Common Sense for Coreference [Unpublished]
• A PDTB-Styled End-to-End Discourse Parser [NUS]
• Shallow Convolutional Neural Network for Implicit Discourse Relation Recognition [emnlp]
• Recursive Deep Models for Discourse Parsing [stanford]

2016 June

• Key-Value Memory Networks for Directly Reading Documents [arXiv]
• Learning to learn by gradient descent by gradient descent [arXiv]
• Multilingual Language Processing From Bytes [arXiv]
• Learning to Communicate with Deep Multi-Agent Reinforcement Learning [arXiv]
• Iterative Alternating Neural Attention for Machine Reading [arXiv]
• Gated-Attention Readers for Text Comprehension [arXiv]

2016 Pre-June

• Globally Normalized Transition-Based Neural Networks [arXiv]
• Adaptive Computation Time for Recurrent Neural Networks [arXiv]
• Neural Machine Translation by Jointly Learning to Align and Translate [arXiv]
• Alpha Go

2015

• Conditional Random Fields as Recurrent Neural Networks [arXiv]
• Skip-Thought Vectors [arXiv]
• Distributed Representations of Sentences and Documents [arXiv]
• A Neural Algorithm of Artistic Style [arXiv]
• Intriguing properties of neural networks [arXiv]
• Difference Target Propagation [arXiv]
• Long Short-Term Memory [cmu]