awesome-deeplearning-resources

Deep Learning

• return to home

Deep learning

• Adaptive Computation Time for Recurrent Neural Networks. arxiv :star:
• A Deep Learning Approach To Multiple Kernel Fusion. arxiv
• Aggregated Residual Transformations for Deep Neural Networks. arxiv tensorflow
• A guide to convolution arithmetic for deep learning. arxiv
• A New Method to Visualize Deep Neural Networks. pdf
• A Persona-Based Neural Conversation Model. pdf
• Architectural Complexity Measures of Recurrent Neural Networks. arxiv
• Associative Long Short-Term Memory. arxiv :star:
• Automatic chemical design using a data-driven continuous representation of molecules. arxiv pytorch
• A Way out of the Odyssey- Analyzing and Combining Recent Insights for LSTMs. arxiv :star:
• Batch Policy Gradient Methods for Improving Neural Conversation Models. url
• Benefits of depth in neural networks. url
• BinaryNet-Training Deep Neural Networks with Weights and Activations Constrained to +1 or -1. arxiv
• Bitwise Neural Networks. pdf
• Bridging the Gaps Between Residual Learning, Recurrent Neural Networks and Visual Cortex. arxiv
• Building Machines That Learn and Think Like People. pdf :star:
• Building Large Machine Reading-Comprehension Datasets using Paragraph Vectors. arxiv
• CNN Image Retrieval Learns from BoW: Unsupervised Fine-Tuning with Hard Examples. arxiv code
• Composing graphical models with neural networks for structured representations and fast inference .arxiv code
• Conditional Generative Moment-Matching Networks. arxiv
• Context Encoders: Feature Learning by Inpainting. arxiv pytorch
• Conversational Contextual Cues-The Case of Personalization and History for Response Ranking. arxiv
• Controlling Output Length in Neural Encoder-Decoders. arxiv code
• Convolutional Neural Networks on Graphs with Fast Localized Spectral Filtering. arxiv code
• Data Programming- Creating Large Training Sets, Quickly. arxiv
• DCM Bandits: Learning to Rank with Multiple Clicks. pdf
• Decoupled Neural Interfaces using Synthetic Gradients. pdf
• DeepChess: End-to-End Deep Neural Network for Automatic Learning in Chess. pdf tensorflow
• DeepMind Lab. url :star:
• Deep API Learning. pdf
• [DeepCoder] DeepCoder: Learning to Write Programs :star:
• [DeepFashion] Powering Robust Clothes Recognition and Retrieval with Rich Annotations. pdf code
• Deep Learning without Poor Local Minima. arxiv :star:
• Deep Learning with Differential Privacy. arxiv tensorflow :star:
• Deep Portfolio Theory. arxiv
• Deeply-Fused Nets. arxiv :star:
• DeepSense: A Unified Deep Learning Framework for Time-Series Mobile Sensing Data Processing. arxiv code
• Densely Connected Convolutional Networks. arxiv pytorch
• Detect, Replace, Refine: Deep Structured Prediction For Pixel Wise Labeling. arxiv code
• [DenseNet] Densely Connected Convolutional Networks. arxiv pytorch :star:
• Density estimation using Real NVP.arxivtensorflow
• Domain Separation Networks. [url]
• [DrMAD] Distilling Reverse-Mode Automatic Differentiation for Optimizing Hyperparameters of Deep Neural Networks.) arxiv code :star:
• Dynamic Neural Turing Machine with Soft and Hard Addressing Schemes. arxiv
• Early Visual Concept Learning with Unsupervised Deep Learning. arxiv code
• Efficient softmax approximation for GPUs. arxiv code
• Efficient Training of Very Deep Neural Networks for Supervised Hashing. arxiv
• Episodic Exploration for Deep Deterministic Policies- An Application to StarCraft Micromanagement Tasks. arxiv
• Event-driven Random Back-Propagation: Enabling Neuromorphic Deep Learning Machines. arxiv
• Fathom: Reference Workloads for Modern Deep Learning Methods.arxiv
• Feedback arcs and node hierarchy in directed networks. arxiv
• FINN: A framework for fast, scalable binarized neural network inference. arxiv code
• FlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networks. arxiv code
• FractalNet-Ultra-Deep Neural Networks without Residuals. arxiv
• [URNN] Full-Capacity Unitary Recurrent Neural Networks. arxiv code :star:
• Fused-Layer CNN Accelerators. pdf
• Generating long and diverse responses with neural conversation models.arxiv
• GRAPH CONVOLUTIONAL NETWORKS. url code :star:
• Hierarchical Multiscale Recurrent Neural Networks. arxiv :star:
• Higher Order Recurrent Neural Networks. arxiv
• Highway and Residual Networks learn Unrolled Iterative Estimation. pdf
• Hyperband: A Novel Bandit-Based Approach to Hyperparameter Optimization. arxiv pytorch :star:
• How to Train Your Deep Neural Network with Dictionary Learning. arxiv
• Improving the Robustness of Deep Neural Networks via Stability Training. arxiv
• Large-Margin Softmax Loss for Convolutional Neural Networks. arxiv
• Latent Predictor Networks for Code Generation. arxiv
• [Normalization] Layer Normalization. arxiv code :star:
• Learning Discriminative Features via Label Consistent Neural Network. arxiv
• Learning End-to-End Goal-Oriented Dialog. arxiv
• Learning Features by Watching Objects Move. arxiv code
• Learning Python Code Suggestion with a Sparse Pointer Network. arxiv code :star:
• Learning to learn by gradient descent by gradient descent. pdf :star:
• Machine Comprehension Using Match-LSTM and Answer Pointer. arxiv
• [AlphaGo] Mastering the game of Go with deep neural networks and tree search. pdf] :star:
• Meta-Unsupervised-Learning: A supervised approach to unsupervised learning. arxiv
• Models, networks and algorithmic complexity. arxiv
• Multivariate Industrial Time Series with Cyber-Attack Simulation: Fault Detection Using an LSTM-based Predictive Data Model.url
• Multiresolution Recurrent Neural Networks- An Application to Dialogue Response Generation. arxiv
• Mutual information for fitting deep nonlinear models. pdf
• Natural-Parameter Networks: A Class of Probabilistic Neural Networks. arxiv
• Neural Paraphrase Generation with Stacked Residual LSTM Networks. arxiv code
• Outrageously Large Neural Networks- The Sparsely-Gated Mixture-of-Experts Layer. pdf
• Overcoming catastrophic forgetting in neural networks. arxiv
• Phased LSTM: Accelerating Recurrent Network Training for Long or Event-based Sequences. arxiv tensorflow :star:
• Pixel Recurrent Neural Networks. arxiv
• Polynomial networks and factorization machines new insights and efficient training algorithms. pdf
• Policy Networks with Two-Stage Training for Dialogue Systems. arxiv
• [PSPNet] Pyramid Scene Parsing Network. arxiv code:star:
• Projected Semi-Stochastic Gradient Descent Method with Mini-Batch Scheme under Weak Strong Convexity Assumption. arxiv
• [QRNN] Quasi-Recurrent Neural Networks. arxiv tensorflow keras pytorch :star:
• RAISR: Rapid and Accurate Image Super Resolution. arxiv :star:
• Recurrent Batch Normalization. arxiv :star:
• Recurrent Dropout without Memory Loss. arxiv :star:
• Recurrent Highway Networks. arxiv
• Residual Networks of Residual Networks- Multilevel Residual Networks. arxiv
• Revisiting Semi-Supervised Learning with Graph Embeddings. arxiv code
• Risk versus Uncertainty in Deep Learning: Bayes, Bootstrap and the Dangers of Dropout. pdf
• RNN-based Encoder-decoder Approach with Word Frequency Estimation. arxiv
• SampleRNN: An Unconditional End-To-End Neural Audio Generation Model. pdf code
• Semantic3D.net: A new Large-scale Point Cloud Classification Benchmark.arxiv code
• Semi-Supervised Classification with Graph Convolutional Networks. arxiv
• SoundNet: Learning Sound Representations from Unlabeled Video. pdf tensorflow :star:
• Structured Receptive Fields in CNNs. arxiv code
• Tagger: Deep Unsupervised Perceptual Grouping. [url]
• Temporal Ensembling for Semi-Supervised Learning. arxiv code
• TensorFlow- A system for large-scale machine learning. pdf :star:
• Tensors and algebra give interpretable groups for crosstalk mechanisms in breast cancer.arxiv
• The Inevitability of Probability- Probabilistic Inference in Generic Neural Networks Trained with Non-Probabilistic Feedback. [url]
• The Predictron: End-To-End Learning and Planning. arxiv code
• Towards an integration of deep learning and neuroscience. arxiv
• Training Recurrent Neural Networks by Diffusion. arxiv]
• Tutorial on Variational Autoencoders.arxiv :star:
• Understanding Deep Convolutional Networks. arxiv :star:
• [ICLR:Best Paper] Understanding deep learning requires rethinking generalization. arxiv :star:
• Understanding deep learning requires rethinking generalization. arxiv code :star:
• Understanding Neural Networks through Representation Erasure. arxiv
• Unsupervised Perceptual Rewards for Imitation Learning.arxiv]
• Using Fast Weights to Attend to the Recent Past. arxiv code
• Value Iteration Networks. arxiv code] :star:
• Variable Computation in Recurrent Neural Networks. arxiv
• Visual Dynamics: Probabilistic Future Frame Synthesis via Cross Convolutional Networks. arxiv tensorflow :star:
• Weight Normalization-A Simple Reparameterization to Accelerate Training of Deep Neural Networks. arxiv code :star:
• Wide Residual Networks. arxiv pytorch:star:
• [Xception] Deep Learning with Depthwise Separable Convolutions. arxiv tensorflow :star:
• Zoneout- Regularizing RNNs by Randomly Preserving Hidden Activations. arxiv :star:

Attention and memory

• Attention Based Recurrent Neural Networks for Online Advertising. pdf]
• Attention-Based Recurrent Neural Network Models for Joint Intent Detection and Slot Filling. arxiv tensorflow :star:
• Can Active Memory Replace Attention? arxiv
• Deep Recurrent Models with Fast-Forward Connections for Neural Machine Translation. arxiv :star:
• Emergent Logical Structure in Vector Representations of Neural Readers. arxiv
• Gated End-to-End Memory Networks. arxiv
• Generating Images from Captions with Attention. arxiv
• GRAM: Graph-based Attention Model for Healthcare Representation Learning. arxiv code
• Hybrid computing using a neural network with dynamic external memory. url :star:
• Hierarchical Memory Networks. arxiv
• Knowing When to Look: Adaptive Attention via A Visual Sentinel for Image Captioning. arxiv
• [LightRNN] LightRNN: Memory and Computation-Efficient Recurrent Neural Networks.arxiv tensorflow:star:
• Paying More Attention to Attention: Improving the Performance of Convolutional Neural Networks via Attention Transfer. arxiv code
• Prioritizing Attention in Fast Data: Principles and Promise. pdf
• Recursive Recurrent Nets with Attention Modeling for OCR in the Wild. pdf :star:
• Reducing Redundant Computations with Flexible Attention. arxiv
• Scan, Attend and Read- End-to-End Handwritten Paragraph Recognition with MDLSTM Attention. arxiv
• Structural Attention Neural Networks for improved sentiment analysis. arxiv
• Survey on the attention based RNN model and its applications in computer vision. arxiv

Generative learning

• Adversarial Examples Detection in Deep Networks with Convolutional Filter Statistics. arxiv
• Adversarial examples in the physical world.arxiv
• Adversarially Learned Inference.arxiv code :star:
• Adversarial Multiclass Classification: A Risk Minimization Perspective. pdf code
• Adversarial Perturbations Against Deep Neural Networks for Malware Classification. arxiv
• Adversarial Training For Sketch Retrieval.arxiv
• A Point Set Generation Network for 3D Object Reconstruction from a Single Image. arxiv code
• Automatic Description Generation from Images- A Survey of Models, Datasets, and Evaluation Measures. pdf
• Automatic Colorization with Deep Convolutional Generative Adversarial Networks. stanford
• Auxiliary Deep Generative Models. arxiv code :star:
• [b-GAN] Unified Framework of Generative Adversarial Networks. pdf] :star:
• Conditional Image Synthesis With Auxiliary Classifier GANs. arxiv code
• Connecting Generative Adversarial Networks and Actor-Critic Methods. arxiv
• Coupled Generative Adversarial Networks. arxiv code
• DARN: a Deep Adversial Residual Network for Intrinsic Image Decomposition. url
• DeMIAN: Deep Modality Invariant Adversarial Network. [url]
• Deep Learning Adversarial Examples. url
• DeepFace: Face Generation using Deep Learning. stanford
• Enabling Dark Energy Science with Deep Generative Models of Galaxy Images. arxiv
• [EnergyGAN] Energy-based Generative Adversarial Network. arxiv code :star:
• [f-GAN] f-GAN: Training Generative Neural Samplers using Variational Divergence Minimization.arxiv :star:
• Generative Image Modeling using Style and Structure Adversarial Networks. arxiv
• Generating Images Part by Part with Composite Generative Adversarial Networks. arxiv
• [GRAN] Generating images with recurrent adversarial networks. pdf :star:
• Generating Images with Perceptual Similarity Metrics based on Deep Networks. arxiv :star:
• Generative Adversarial Imitation Learning. arxiv code
• [VGNA] Generative Adversarial Networks as Variational Training of Energy Based Models. arxiv code
• Generative Adversarial Nets from a Density Ratio Estimation Perspective. arxiv
• [iGNA] Generative Visual Manipulation on the Natural Image Manifold. berkeley code :star:
• Generating Videos with Scene Dynamics. pdf code tensorflow:star:
• How to Train a GAN. code :star:
• [Pix2Pix]Image-to-Image Translation with Conditional Adversarial Networks. arxiv tensorflow :star:
• [Improved GAN] Image-Text Multi-Modal Representation Learning by Adversarial Backpropagation. arxiv :star:
• Improved Techniques for Training GANs.arxiv code tensorflow :star:
• [InfoGAN] Interpretable Representation Learning by Information Maximizing Generative Adversarial Nets. arxiv code tensorflow :star:
• Learning a Probabilistic Latent Space of Object Shapes via 3D Generative-Adversarial Modeling. arxiv tensorflow
• [SimGAN] Learning from Simulated and Unsupervised Images through Adversarial Training. arxiv keras :star:
• Learning in Implicit Generative Models. arxiv
• Learning to Protect Communications with Adversarial Neural Cryptography. arxiv
• Least Squares Generative Adversarial Networks. arxiv :star:
• Medical Image Synthesis with Context-Aware Generative Adversarial Networks. arxiv
• Mode Regularized Generative Adversarial Networks. arxiv :star:
• Neural Fill: Content Aware Image Fill with Generative Adversarial Neural Networks. stanford
• NIPS 2016 Tutorial: Generative Adversarial Networks. arxiv :star:
• [SRGAN] Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network. arxiv :star:
• [DCGAN use] Semantic Image Inpainting with Perceptual and Contextual Losses.arxiv :star:
• Semi-Supervised Learning with Generative Adversarial Networks. arxiv
• [SeqGAN] Sequence Generative Adversarial Nets with Policy Gradient. arxiv code :star:
• Simple black-box adversarial perturbations for deep networks. url
• Stick-Breaking Variational Autoencoders. arxiv code
• Stochastic Video Prediction with Deep Conditional Generative Models. stanford
• Task Specific Adversarial Cost Function. arxiv
• Temporal Generative Adversarial Nets with Singular Value Clipping. arxiv code
• Towards Principled Methods for Training Generative Adversarial Networks. arxiv]
• Understanding deep learning requires rethinking generalization.arxiv :star:
• Unsupervised domain adaptation in brain lesion segmentation with adversarial networks.arxiv code
• Unrolled Generative Adversarial Networks. arxiv code
• Variational Graph Auto-Encoders. arxiv tensorflow :star:

Transfer learning

• A survey of transfer learning. url :star:
• Building Machines That Learn and Think Like People. arxiv
• Fast color transfer from multiple images. arxiv
• Perceptual Losses for Real-Time Style Transfer and Super-Resolution.arxiv code :star:
• Personalizing a Dialogue System with Transfer Learning. arxiv
• Pixel-Level Domain Transfer. arxiv
• Progressive Neural Networks. arxiv :star:
• Semantic Style Transfer and Turning Two-Bit Doodles into Fine Artworks.arxivcode :star:
• [Best Paper]Semi-supervised Knowledge Transfer for Deep Learning from Private Training Data. arxiv tensorflow :star:
• FastMask: Segment Multi-scale Object Candidates in One Shot.arxiv
• Learning feed-forward one-shot learners. arxiv
• Low-shot Visual Recognition by Shrinking and Hallucinating Features. arxiv :star:
• Matching Networks for One Shot Learning. arxiv
• One-Shot Generalization in Deep Generative Models. pdf :star:
• One-shot Learning with Memory-Augmented Neural Networks. arxiv tensorflow:star:
• One-Shot Video Object Segmentation. arxiv tensorflow
• Tinkering Under the Hood: Interactive Zero-Shot Learning with Net Surgery. arxiv

This site is open source. Improve this page.