for oral, found 10/15 papers on arxiv with library counts: 64 Reinforcement Learning with Unsupervised Auxiliary Tasks 44 Neural Architecture Search with Reinforcement Learning 38 Understanding deep learning requires rethinking generalization 28 Towards Principled Methods for Training Generative Adversarial Networks 22 Learning End-to-End Goal-Oriented Dialog 19 Q-Prop: Sample-Efficient Policy Gradient with An Off-Policy Critic 13 Learning to Act by Predicting the Future 12 Amortised MAP Inference for Image Super-resolution 8 Multi-Agent Cooperation and the Emergence of (Natural) Language 8 End-to-end Optimized Image Compression --------------- for poster, found 113/183 papers on arxiv with library counts: 149 Adversarial Feature Learning 147 Hierarchical Multiscale Recurrent Neural Networks 140 Recurrent Batch Normalization 80 HyperNetworks 79 FractalNet: Ultra-Deep Neural Networks without Residuals 73 Zoneout: Regularizing RNNs by Randomly Preserving Hidden Activations 62 Unrolled Generative Adversarial Networks 52 Adversarially Learned Inference 49 Quasi-Recurrent Neural Networks 48 Do Deep Convolutional Nets Really Need to be Deep and Convolutional? 46 Neural Photo Editing with Introspective Adversarial Networks 43 An Actor-Critic Algorithm for Sequence Prediction 41 A Learned Representation For Artistic Style 37 Structured Attention Networks 33 Mollifying Networks 30 DeepCoder: Learning to Write Programs 28 SGDR: Stochastic Gradient Descent with Warm Restarts 27 Learning to Navigate in Complex Environments 27 Generative Multi-Adversarial Networks 26 Soft Weight-Sharing for Neural Network Compression 25 Pruning Filters for Efficient ConvNets 24 Why Deep Neural Networks for Function Approximation? 24 Mode Regularized Generative Adversarial Networks 24 Dialogue Learning With Human-in-the-Loop 24 Designing Neural Network Architectures using Reinforcement Learning 23 PGQ: Combining policy gradient and Q-learning 22 Frustratingly Short Attention Spans in Neural Language Modeling 21 Tracking the World State with Recurrent Entity Networks 21 Deep Probabilistic Programming 20 Density estimation using Real NVP 20 Adversarial Training Methods for Semi-Supervised Text Classification 19 Semi-Supervised Classification with Graph Convolutional Networks 19 PixelVAE: A Latent Variable Model for Natural Images 19 Learning to Optimize 19 Learning a Natural Language Interface with Neural Programmer 19 Entropy-SGD: Biasing Gradient Descent Into Wide Valleys 19 Dynamic Coattention Networks For Question Answering 18 PixelCNN++: Improving the PixelCNN with Discretized Logistic Mixture Likelihood and Other Modifications 18 Generalizing Skills with Semi-Supervised Reinforcement Learning 18 Deep Learning with Dynamic Computation Graphs 18 Automatic Rule Extraction from Long Short Term Memory Networks 18 Adversarial Machine Learning at Scale 17 Learning through Dialogue Interactions by Asking Questions 16 Learning to Perform Physics Experiments via Deep Reinforcement Learning 16 Categorical Reparameterization with Gumbel-Softmax 15 Sample Efficient Actor-Critic with Experience Replay 14 Variational Lossy Autoencoder 14 Identity Matters in Deep Learning 14 Bidirectional Attention Flow for Machine Comprehension 13 Towards a Neural Statistician 13 Recurrent Mixture Density Network for Spatiotemporal Visual Attention 13 On Detecting Adversarial Perturbations 12 Trained Ternary Quantization 12 Improving Policy Gradient by Exploring Under-appreciated Rewards 12 Capacity and Trainability in Recurrent Neural Networks 11 SampleRNN: An Unconditional End-to-End Neural Audio Generation Model 11 Machine Comprehension Using Match-LSTM and Answer Pointer 11 Latent Sequence Decompositions 11 Calibrating Energy-based Generative Adversarial Networks 10 Unsupervised Cross-Domain Image Generation 10 Learning to Remember Rare Events 10 Highway and Residual Networks learn Unrolled Iterative Estimation 9 TopicRNN: A Recurrent Neural Network with Long-Range Semantic Dependency 9 Steerable CNNs 9 Query-Reduction Networks for Question Answering 9 Lossy Image Compression with Compressive Autoencoders 9 Learning to Compose Words into Sentences with Reinforcement Learning 8 Stick-Breaking Variational Autoencoders 8 Deep Variational Information Bottleneck 8 Batch Policy Gradient Methods for Improving Neural Conversation Models 7 Discrete Variational Autoencoders 7 Data Noising as Smoothing in Neural Network Language Models 6 Variable Computation in Recurrent Neural Networks 6 Sigma Delta Quantized Networks 6 Dropout with Expectation-linear Regularization 6 Delving into Transferable Adversarial Examples and Black-box Attacks 6 A Compositional Object-Based Approach to Learning Physical Dynamics 5 Towards the Limit of Network Quantization 5 Tighter bounds lead to improved classifiers 5 Pointer Sentinel Mixture Models 5 On the Quantitative Analysis of Decoder-Based Generative Models 5 Neuro-Symbolic Program Synthesis 5 Lie-Access Neural Turing Machines 5 Learning to superoptimize programs 5 Learning Features of Music From Scratch 5 Improving Neural Language Models with a Continuous Cache 5 Deep Biaffine Attention for Neural Dependency Parsing 4 Temporal Ensembling for Semi-Supervised Learning 4 Diet Networks: Thin Parameters for Fat Genomics 4 DeepDSL: A Compilation-based Domain-Specific Language for Deep Learning 4 DSD: Dense-Sparse-Dense Training for Deep Neural Networks 4 A recurrent neural network without chaos 3 Trusting SVM for Piecewise Linear CNNs 3 The Neural Noisy Channel 3 Revisiting Classifier Two-Sample Tests 3 Regularizing CNNs with Locally Constrained Decorrelations 3 Optimal Binary Autoencoding with Pairwise Correlations 3 Loss-aware Binarization of Deep Networks 3 Learning Recurrent Representations for Hierarchical Behavior Modeling 3 EPOpt: Learning Robust Neural Network Policies Using Model Ensembles 3 Deep Information Propagation 2 Words or Characters? Fine-grained Gating for Reading Comprehension 2 Topology and Geometry of Half-Rectified Network Optimization 2 Maximum Entropy Flow Networks 2 Incorporating long-range consistency in CNN-based texture generation 2 Hadamard Product for Low-rank Bilinear Pooling 1 Multi-view Recurrent Neural Acoustic Word Embeddings 1 Inductive Bias of Deep Convolutional Networks through Pooling Geometry 1 Geometry of Polysemy 1 Autoencoding Variational Inference For Topic Models 1 A STRUCTURED SELF-ATTENTIVE SENTENCE EMBEDDING 0 Deep Multi-task Representation Learning: A Tensor Factorisation Approach 0 A Compare-Aggregate Model for Matching Text Sequences --------------- for workshop, found 23/48 papers on arxiv with library counts: 60 Adversarial examples in the physical world 31 Learning in Implicit Generative Models 16 Surprise-Based Intrinsic Motivation for Deep Reinforcement Learning 14 Multiplicative LSTM for sequence modelling 13 Efficient Softmax Approximation for GPUs 12 RenderGAN: Generating Realistic Labeled Data 12 Generalizable Features From Unsupervised Learning 10 Programming With a Differentiable Forth Interpreter 8 Gated Multimodal Units for Information Fusion 8 Deep Learning with Sets and Point Clouds 7 Unsupervised Perceptual Rewards for Imitation Learning 5 Song From PI: A Musically Plausible Network for Pop Music Generation 5 Modular Multitask Reinforcement Learning with Policy Sketches 5 A Differentiable Physics Engine for Deep Learning in Robotics 4 Exponential Machines 4 Dataset Augmentation in Feature Space 3 Semi-supervised deep learning by metric embedding 2 Adaptive Feature Abstraction for Translating Video to Language 1 Modularized Morphing of Neural Networks 1 Learning Continuous Semantic Representations of Symbolic Expressions 1 Extrapolation and learning equations 0 Online Structure Learning for Sum-Product Networks with Gaussian Leaves 0 Bit-Pragmatic Deep Neural Network Computing --------------- for reject, found 58/245 papers on arxiv with library counts: 46 The Predictron: End-To-End Learning and Planning 39 RL^2: Fast Reinforcement Learning via Slow Reinforcement Learning 35 Understanding intermediate layers using linear classifier probes 33 Hierarchical Memory Networks 31 An Analysis of Deep Neural Network Models for Practical Applications 20 Low-rank passthrough neural networks 19 Higher Order Recurrent Neural Networks 18 Adding Gradient Noise Improves Learning for Very Deep Networks 16 Unsupervised Pretraining for Sequence to Sequence Learning 16 A Joint Many-Task Model: Growing a Neural Network for Multiple NLP Tasks 15 Adversarial examples for generative models 14 Gated-Attention Readers for Text Comprehension 13 Extensions and Limitations of the Neural GPU 12 Warped Convolutions: Efficient Invariance to Spatial Transformations 11 Neural Combinatorial Optimization with Reinforcement Learning 11 Memory-augmented Attention Modelling for Videos 10 GRAM: Graph-based Attention Model for Healthcare Representation Learning 9 Wav2Letter: an End-to-End ConvNet-based Speech Recognition System 9 Understanding trained CNNs by indexing neuron selectivity 9 The Power of Sparsity in Convolutional Neural Networks 9 Improving Stochastic Gradient Descent with Feedback 8 Towards Information-Seeking Agents 8 NEWSQA: A MACHINE COMPREHENSION DATASET 8 LipNet: End-to-End Sentence-level Lipreading 7 Generative Adversarial Parallelization 7 Efficient Summarization with Read-Again and Copy Mechanism 6 Multi-task learning with deep model based reinforcement learning 6 Multi-modal Variational Encoder-Decoders 6 End-to-End Answer Chunk Extraction and Ranking for Reading Comprehension 6 Boosting Image Captioning with Attributes 6 Beyond Fine Tuning: A Modular Approach to Learning on Small Data 5 Structured Sequence Modeling with Graph Convolutional Recurrent Networks 5 Human perception in computer vision 5 Cooperative Training of Descriptor and Generator Networks 4 Options Discovery with Budgeted Reinforcement Learning 4 Incremental Sequence Learning 4 FastText.zip: Compressing text classification models 3 Simple Black-Box Adversarial Perturbations for Deep Networks 3 Sequence to Sequence Transduction with Hard Monotonic Attention 3 Playing SNES in the Retro Learning Environment 3 Multi-view Generative Adversarial Networks 3 Joint Multimodal Learning with Deep Generative Models 3 Here's My Point: Argumentation Mining with Pointer Networks 3 Boosted Generative Models 3 Attentive Recurrent Comparators 2 Two Methods for Wild Variational Inference 2 Fast Adaptation in Generative Models with Generative Matching Networks 2 Efficient iterative policy optimization 1 Reference-Aware Language Models 1 Neural Machine Translation with Latent Semantic of Image and Text 1 Near-Data Processing for Machine Learning 1 Intelligible Language Modeling with Input Switched Affine Networks 1 Generating Long and Diverse Responses with Neural Conversation Models 1 Deep Generalized Canonical Correlation Analysis 1 A Context-aware Attention Network for Interactive Question Answering 0 Transformation-based Models of Video Sequences 0 Exploring LOTS in Deep Neural Networks 0 Annealing Gaussian into ReLU: a New Sampling Strategy for Leaky-ReLU RBM --------------- for oral, found 10/15 papers on arxiv with library counts: 64 Reinforcement Learning with Unsupervised Auxiliary Tasks 44 Neural Architecture Search with Reinforcement Learning 38 Understanding deep learning requires rethinking generalization 28 Towards Principled Methods for Training Generative Adversarial Networks 22 Learning End-to-End Goal-Oriented Dialog 19 Q-Prop: Sample-Efficient Policy Gradient with An Off-Policy Critic 13 Learning to Act by Predicting the Future 12 Amortised MAP Inference for Image Super-resolution 8 Multi-Agent Cooperation and the Emergence of (Natural) Language 8 End-to-end Optimized Image Compression --------------- for poster, found 113/183 papers on arxiv with library counts: 149 Adversarial Feature Learning 147 Hierarchical Multiscale Recurrent Neural Networks 140 Recurrent Batch Normalization 80 HyperNetworks 79 FractalNet: Ultra-Deep Neural Networks without Residuals 73 Zoneout: Regularizing RNNs by Randomly Preserving Hidden Activations 62 Unrolled Generative Adversarial Networks 52 Adversarially Learned Inference 49 Quasi-Recurrent Neural Networks 48 Do Deep Convolutional Nets Really Need to be Deep and Convolutional? 46 Neural Photo Editing with Introspective Adversarial Networks 43 An Actor-Critic Algorithm for Sequence Prediction 41 A Learned Representation For Artistic Style 37 Structured Attention Networks 33 Mollifying Networks 30 DeepCoder: Learning to Write Programs 28 SGDR: Stochastic Gradient Descent with Warm Restarts 27 Learning to Navigate in Complex Environments 27 Generative Multi-Adversarial Networks 26 Soft Weight-Sharing for Neural Network Compression 25 Pruning Filters for Efficient ConvNets 24 Why Deep Neural Networks for Function Approximation? 24 Mode Regularized Generative Adversarial Networks 24 Dialogue Learning With Human-in-the-Loop 24 Designing Neural Network Architectures using Reinforcement Learning 23 PGQ: Combining policy gradient and Q-learning 22 Frustratingly Short Attention Spans in Neural Language Modeling 21 Tracking the World State with Recurrent Entity Networks 21 Deep Probabilistic Programming 20 Density estimation using Real NVP 20 Adversarial Training Methods for Semi-Supervised Text Classification 19 Semi-Supervised Classification with Graph Convolutional Networks 19 PixelVAE: A Latent Variable Model for Natural Images 19 Learning to Optimize 19 Learning a Natural Language Interface with Neural Programmer 19 Entropy-SGD: Biasing Gradient Descent Into Wide Valleys 19 Dynamic Coattention Networks For Question Answering 18 PixelCNN++: Improving the PixelCNN with Discretized Logistic Mixture Likelihood and Other Modifications 18 Generalizing Skills with Semi-Supervised Reinforcement Learning 18 Deep Learning with Dynamic Computation Graphs 18 Automatic Rule Extraction from Long Short Term Memory Networks 18 Adversarial Machine Learning at Scale 17 Learning through Dialogue Interactions by Asking Questions 16 Learning to Perform Physics Experiments via Deep Reinforcement Learning 16 Categorical Reparameterization with Gumbel-Softmax 15 Sample Efficient Actor-Critic with Experience Replay 14 Variational Lossy Autoencoder 14 Identity Matters in Deep Learning 14 Bidirectional Attention Flow for Machine Comprehension 13 Towards a Neural Statistician 13 Recurrent Mixture Density Network for Spatiotemporal Visual Attention 13 On Detecting Adversarial Perturbations 12 Trained Ternary Quantization 12 Improving Policy Gradient by Exploring Under-appreciated Rewards 12 Capacity and Trainability in Recurrent Neural Networks 11 SampleRNN: An Unconditional End-to-End Neural Audio Generation Model 11 Machine Comprehension Using Match-LSTM and Answer Pointer 11 Latent Sequence Decompositions 11 Calibrating Energy-based Generative Adversarial Networks 10 Unsupervised Cross-Domain Image Generation 10 Learning to Remember Rare Events 10 Highway and Residual Networks learn Unrolled Iterative Estimation 9 TopicRNN: A Recurrent Neural Network with Long-Range Semantic Dependency 9 Steerable CNNs 9 Query-Reduction Networks for Question Answering 9 Lossy Image Compression with Compressive Autoencoders 9 Learning to Compose Words into Sentences with Reinforcement Learning 8 Stick-Breaking Variational Autoencoders 8 Deep Variational Information Bottleneck 8 Batch Policy Gradient Methods for Improving Neural Conversation Models 7 Discrete Variational Autoencoders 7 Data Noising as Smoothing in Neural Network Language Models 6 Variable Computation in Recurrent Neural Networks 6 Sigma Delta Quantized Networks 6 Dropout with Expectation-linear Regularization 6 Delving into Transferable Adversarial Examples and Black-box Attacks 6 A Compositional Object-Based Approach to Learning Physical Dynamics 5 Towards the Limit of Network Quantization 5 Tighter bounds lead to improved classifiers 5 Pointer Sentinel Mixture Models 5 On the Quantitative Analysis of Decoder-Based Generative Models 5 Neuro-Symbolic Program Synthesis 5 Lie-Access Neural Turing Machines 5 Learning to superoptimize programs 5 Learning Features of Music From Scratch 5 Improving Neural Language Models with a Continuous Cache 5 Deep Biaffine Attention for Neural Dependency Parsing 4 Temporal Ensembling for Semi-Supervised Learning 4 Diet Networks: Thin Parameters for Fat Genomics 4 DeepDSL: A Compilation-based Domain-Specific Language for Deep Learning 4 DSD: Dense-Sparse-Dense Training for Deep Neural Networks 4 A recurrent neural network without chaos 3 Trusting SVM for Piecewise Linear CNNs 3 The Neural Noisy Channel 3 Revisiting Classifier Two-Sample Tests 3 Regularizing CNNs with Locally Constrained Decorrelations 3 Optimal Binary Autoencoding with Pairwise Correlations 3 Loss-aware Binarization of Deep Networks 3 Learning Recurrent Representations for Hierarchical Behavior Modeling 3 EPOpt: Learning Robust Neural Network Policies Using Model Ensembles 3 Deep Information Propagation 2 Words or Characters? Fine-grained Gating for Reading Comprehension 2 Topology and Geometry of Half-Rectified Network Optimization 2 Maximum Entropy Flow Networks 2 Incorporating long-range consistency in CNN-based texture generation 2 Hadamard Product for Low-rank Bilinear Pooling 1 Multi-view Recurrent Neural Acoustic Word Embeddings 1 Inductive Bias of Deep Convolutional Networks through Pooling Geometry 1 Geometry of Polysemy 1 Autoencoding Variational Inference For Topic Models 1 A STRUCTURED SELF-ATTENTIVE SENTENCE EMBEDDING 0 Deep Multi-task Representation Learning: A Tensor Factorisation Approach 0 A Compare-Aggregate Model for Matching Text Sequences --------------- for workshop, found 23/48 papers on arxiv with library counts: 60 Adversarial examples in the physical world 31 Learning in Implicit Generative Models 16 Surprise-Based Intrinsic Motivation for Deep Reinforcement Learning 14 Multiplicative LSTM for sequence modelling 13 Efficient Softmax Approximation for GPUs 12 RenderGAN: Generating Realistic Labeled Data 12 Generalizable Features From Unsupervised Learning 10 Programming With a Differentiable Forth Interpreter 8 Gated Multimodal Units for Information Fusion 8 Deep Learning with Sets and Point Clouds 7 Unsupervised Perceptual Rewards for Imitation Learning 5 Song From PI: A Musically Plausible Network for Pop Music Generation 5 Modular Multitask Reinforcement Learning with Policy Sketches 5 A Differentiable Physics Engine for Deep Learning in Robotics 4 Exponential Machines 4 Dataset Augmentation in Feature Space 3 Semi-supervised deep learning by metric embedding 2 Adaptive Feature Abstraction for Translating Video to Language 1 Modularized Morphing of Neural Networks 1 Learning Continuous Semantic Representations of Symbolic Expressions 1 Extrapolation and learning equations 0 Online Structure Learning for Sum-Product Networks with Gaussian Leaves 0 Bit-Pragmatic Deep Neural Network Computing --------------- for reject, found 58/245 papers on arxiv with library counts: 46 The Predictron: End-To-End Learning and Planning 39 RL^2: Fast Reinforcement Learning via Slow Reinforcement Learning 35 Understanding intermediate layers using linear classifier probes 33 Hierarchical Memory Networks 31 An Analysis of Deep Neural Network Models for Practical Applications 20 Low-rank passthrough neural networks 19 Higher Order Recurrent Neural Networks 18 Adding Gradient Noise Improves Learning for Very Deep Networks 16 Unsupervised Pretraining for Sequence to Sequence Learning 16 A Joint Many-Task Model: Growing a Neural Network for Multiple NLP Tasks 15 Adversarial examples for generative models 14 Gated-Attention Readers for Text Comprehension 13 Extensions and Limitations of the Neural GPU 12 Warped Convolutions: Efficient Invariance to Spatial Transformations 11 Neural Combinatorial Optimization with Reinforcement Learning 11 Memory-augmented Attention Modelling for Videos 10 GRAM: Graph-based Attention Model for Healthcare Representation Learning 9 Wav2Letter: an End-to-End ConvNet-based Speech Recognition System 9 Understanding trained CNNs by indexing neuron selectivity 9 The Power of Sparsity in Convolutional Neural Networks 9 Improving Stochastic Gradient Descent with Feedback 8 Towards Information-Seeking Agents 8 NEWSQA: A MACHINE COMPREHENSION DATASET 8 LipNet: End-to-End Sentence-level Lipreading 7 Generative Adversarial Parallelization 7 Efficient Summarization with Read-Again and Copy Mechanism 6 Multi-task learning with deep model based reinforcement learning 6 Multi-modal Variational Encoder-Decoders 6 End-to-End Answer Chunk Extraction and Ranking for Reading Comprehension 6 Boosting Image Captioning with Attributes 6 Beyond Fine Tuning: A Modular Approach to Learning on Small Data 5 Structured Sequence Modeling with Graph Convolutional Recurrent Networks 5 Human perception in computer vision 5 Cooperative Training of Descriptor and Generator Networks 4 Options Discovery with Budgeted Reinforcement Learning 4 Incremental Sequence Learning 4 FastText.zip: Compressing text classification models 3 Simple Black-Box Adversarial Perturbations for Deep Networks 3 Sequence to Sequence Transduction with Hard Monotonic Attention 3 Playing SNES in the Retro Learning Environment 3 Multi-view Generative Adversarial Networks 3 Joint Multimodal Learning with Deep Generative Models 3 Here's My Point: Argumentation Mining with Pointer Networks 3 Boosted Generative Models 3 Attentive Recurrent Comparators 2 Two Methods for Wild Variational Inference 2 Fast Adaptation in Generative Models with Generative Matching Networks 2 Efficient iterative policy optimization 1 Reference-Aware Language Models 1 Neural Machine Translation with Latent Semantic of Image and Text 1 Near-Data Processing for Machine Learning 1 Intelligible Language Modeling with Input Switched Affine Networks 1 Generating Long and Diverse Responses with Neural Conversation Models 1 Deep Generalized Canonical Correlation Analysis 1 A Context-aware Attention Network for Interactive Question Answering 0 Transformation-based Models of Video Sequences 0 Exploring LOTS in Deep Neural Networks 0 Annealing Gaussian into ReLU: a New Sampling Strategy for Leaky-ReLU RBM ---------------