# Differences

This shows you the differences between two versions of the page.

iclr2017:conference_posters [2017/03/29 09:23] hugo |
iclr2017:conference_posters [2017/04/23 09:26] (current) hugo |
||
---|---|---|---|

Line 2: | Line 2: | ||

Below are the Conference Track papers presented at each of the poster sessions (on Monday, Tuesday or Wednesday, in the morning or evening). To find a paper, look for the poster with the corresponding number in the area dedicated to the Conference Track. | Below are the Conference Track papers presented at each of the poster sessions (on Monday, Tuesday or Wednesday, in the morning or evening). To find a paper, look for the poster with the corresponding number in the area dedicated to the Conference Track. | ||

+ | |||

+ | ======Note to the Presenters======= | ||

+ | Each poster panel is 2 meters large and 1 meter tall.\\ | ||

+ | If needed, tape will be provided to fix your poster. | ||

+ | |||

<html><div id='monday_morning'></div></html> | <html><div id='monday_morning'></div></html> | ||

Line 16: | Line 21: | ||

C10: Paying More Attention to Attention: Improving the Performance of Convolutional Neural Networks via Attention Transfer\\ | C10: Paying More Attention to Attention: Improving the Performance of Convolutional Neural Networks via Attention Transfer\\ | ||

C11: Pruning Filters for Efficient ConvNets\\ | C11: Pruning Filters for Efficient ConvNets\\ | ||

- | C12: Optimization as a Model for Few-Shot Learning\\ | + | C12: Stick-Breaking Variational Autoencoders\\ |

- | C13: Understanding deep learning requires rethinking generalization\\ | + | C13: Identity Matters in Deep Learning\\ |

C14: On Large-Batch Training for Deep Learning: Generalization Gap and Sharp Minima\\ | C14: On Large-Batch Training for Deep Learning: Generalization Gap and Sharp Minima\\ | ||

C15: Recurrent Hidden Semi-Markov Model\\ | C15: Recurrent Hidden Semi-Markov Model\\ | ||

Line 53: | Line 58: | ||

C11: PixelCNN++: A PixelCNN Implementation with Discretized Logistic Mixture Likelihood and Other Modifications\\ | C11: PixelCNN++: A PixelCNN Implementation with Discretized Logistic Mixture Likelihood and Other Modifications\\ | ||

C12: Learning to Optimize\\ | C12: Learning to Optimize\\ | ||

- | C13: Training Compressed Fully-Connected Networks with a Density-Diversity Penalty\\ | + | C13: Do Deep Convolutional Nets Really Need to be Deep and Convolutional?\\ |

C14: Optimal Binary Autoencoding with Pairwise Correlations\\ | C14: Optimal Binary Autoencoding with Pairwise Correlations\\ | ||

C15: On the Quantitative Analysis of Decoder-Based Generative Models\\ | C15: On the Quantitative Analysis of Decoder-Based Generative Models\\ | ||

- | C16: Learning to Remember Rare Events\\ | + | C16: Adversarial machine learning at scale\\ |

C17: Transfer Learning for Sequence Tagging with Hierarchical Recurrent Networks\\ | C17: Transfer Learning for Sequence Tagging with Hierarchical Recurrent Networks\\ | ||

C18: Capacity and Learnability in Recurrent Neural Networks\\ | C18: Capacity and Learnability in Recurrent Neural Networks\\ | ||

Line 62: | Line 67: | ||

C20: Exploring Sparsity in Recurrent Neural Networks\\ | C20: Exploring Sparsity in Recurrent Neural Networks\\ | ||

C21: Structured Attention Networks\\ | C21: Structured Attention Networks\\ | ||

- | C22: Zoneout: Regularizing RNNs by Randomly Preserving Hidden Activations\\ | + | C22: Learning to Repeat: Fine Grained Action Repetition for Deep Reinforcement Learning\\ |

C23: Variational Lossy Autoencoder\\ | C23: Variational Lossy Autoencoder\\ | ||

C24: Learning to Query, Reason, and Answer Questions On Ambiguous Texts\\ | C24: Learning to Query, Reason, and Answer Questions On Ambiguous Texts\\ | ||

Line 69: | Line 74: | ||

C27: Data Noising as Smoothing in Neural Network Language Models\\ | C27: Data Noising as Smoothing in Neural Network Language Models\\ | ||

C28: Neural Variational Inference For Topic Models\\ | C28: Neural Variational Inference For Topic Models\\ | ||

- | C29: Words or Characters? Fine-grained Gating for Reading Comprehension\\ | + | C29: Bidirectional Attention Flow for Machine Comprehension\\ |

C30: Q-Prop: Sample-Efficient Policy Gradient with An Off-Policy Critic\\ | C30: Q-Prop: Sample-Efficient Policy Gradient with An Off-Policy Critic\\ | ||

C31: Stochastic Neural Networks for Hierarchical Reinforcement Learning\\ | C31: Stochastic Neural Networks for Hierarchical Reinforcement Learning\\ | ||

Line 78: | Line 83: | ||

====Tuesday Morning (April 25th, 10:30am to 12:30pm)==== | ====Tuesday Morning (April 25th, 10:30am to 12:30pm)==== | ||

C1: DeepDSL: A Compilation-based Domain-Specific Language for Deep Learning\\ | C1: DeepDSL: A Compilation-based Domain-Specific Language for Deep Learning\\ | ||

- | C2: SampleRNN: An Unconditional End-to-End Neural Audio Generation Model\\ | + | C2: A SELF-ATTENTIVE SENTENCE EMBEDDING\\ |

C3: Deep Probabilistic Programming\\ | C3: Deep Probabilistic Programming\\ | ||

C4: Lie-Access Neural Turing Machines\\ | C4: Lie-Access Neural Turing Machines\\ | ||

Line 103: | Line 108: | ||

C25: Query-Reduction Networks for Question Answering\\ | C25: Query-Reduction Networks for Question Answering\\ | ||

C26: Machine Comprehension Using Match-LSTM and Answer Pointer\\ | C26: Machine Comprehension Using Match-LSTM and Answer Pointer\\ | ||

- | C27: Bidirectional Attention Flow for Machine Comprehension\\ | + | C27: Words or Characters? Fine-grained Gating for Reading Comprehension\\ |

C28: Dynamic Coattention Networks For Question Answering\\ | C28: Dynamic Coattention Networks For Question Answering\\ | ||

C29: Multi-view Recurrent Neural Acoustic Word Embeddings\\ | C29: Multi-view Recurrent Neural Acoustic Word Embeddings\\ | ||

Line 112: | Line 117: | ||

<html><div id='tuesday_afternoon'></div></html> | <html><div id='tuesday_afternoon'></div></html> | ||

- | ====Tuesday Afternoon (April 25th, 4:30pm to 6:30pm)==== | + | ====Tuesday Afternoon (April 25th, 2:00pm to 4:00pm)==== |

C1: Sigma Delta Quantized Networks\\ | C1: Sigma Delta Quantized Networks\\ | ||

C2: Paleo: A Performance Model for Deep Neural Networks\\ | C2: Paleo: A Performance Model for Deep Neural Networks\\ | ||

Line 137: | Line 142: | ||

C23: Variable Computation in Recurrent Neural Networks\\ | C23: Variable Computation in Recurrent Neural Networks\\ | ||

C24: Deep Variational Information Bottleneck\\ | C24: Deep Variational Information Bottleneck\\ | ||

- | C25: A SELF-ATTENTIVE SENTENCE EMBEDDING\\ | + | C25: SampleRNN: An Unconditional End-to-End Neural Audio Generation Model\\ |

C26: TopicRNN: A Recurrent Neural Network with Long-Range Semantic Dependency\\ | C26: TopicRNN: A Recurrent Neural Network with Long-Range Semantic Dependency\\ | ||

C27: Frustratingly Short Attention Spans in Neural Language Modeling\\ | C27: Frustratingly Short Attention Spans in Neural Language Modeling\\ | ||

- | C28: Offline Bilingual Word Vectors Without a Dictionary\\ | + | C28: Offline Bilingual Word Vectors, Orthogonal Transformations and the Inverted Softmax\\ |

C29: LEARNING A NATURAL LANGUAGE INTERFACE WITH NEURAL PROGRAMMER\\ | C29: LEARNING A NATURAL LANGUAGE INTERFACE WITH NEURAL PROGRAMMER\\ | ||

C30: Designing Neural Network Architectures using Reinforcement Learning\\ | C30: Designing Neural Network Architectures using Reinforcement Learning\\ | ||

Line 171: | Line 176: | ||

C21: Temporal Ensembling for Semi-Supervised Learning\\ | C21: Temporal Ensembling for Semi-Supervised Learning\\ | ||

C22: On Detecting Adversarial Perturbations\\ | C22: On Detecting Adversarial Perturbations\\ | ||

- | C23: Identity Matters in Deep Learning\\ | + | C23: Understanding deep learning requires rethinking generalization\\ |

C24: Adversarial Feature Learning\\ | C24: Adversarial Feature Learning\\ | ||

C25: Learning through Dialogue Interactions\\ | C25: Learning through Dialogue Interactions\\ | ||

Line 195: | Line 200: | ||

C9: Neural Photo Editing with Introspective Adversarial Networks\\ | C9: Neural Photo Editing with Introspective Adversarial Networks\\ | ||

C10: A Learned Representation For Artistic Style\\ | C10: A Learned Representation For Artistic Style\\ | ||

- | C11: Adversarial Machine Learning at Scale\\ | + | C11: Learning to Remember Rare Events\\ |

- | C12: Stick-Breaking Variational Autoencoders\\ | + | C12: Optimization as a Model for Few-Shot Learning\\ |

C13: Support Regularized Sparse Coding and Its Fast Encoder\\ | C13: Support Regularized Sparse Coding and Its Fast Encoder\\ | ||

C14: Discrete Variational Autoencoders\\ | C14: Discrete Variational Autoencoders\\ | ||

- | C15: Do Deep Convolutional Nets Really Need to be Deep and Convolutional?\\ | + | C15: Training Compressed Fully-Connected Networks with a Density-Diversity Penalty\\ |

C16: Efficient Representation of Low-Dimensional Manifolds using Deep Networks\\ | C16: Efficient Representation of Low-Dimensional Manifolds using Deep Networks\\ | ||

C17: Semi-Supervised Classification with Graph Convolutional Networks\\ | C17: Semi-Supervised Classification with Graph Convolutional Networks\\ | ||

Line 214: | Line 219: | ||

C28: Reasoning with Memory Augmented Neural Networks for Language Comprehension\\ | C28: Reasoning with Memory Augmented Neural Networks for Language Comprehension\\ | ||

C29: Dialogue Learning With Human-in-the-Loop\\ | C29: Dialogue Learning With Human-in-the-Loop\\ | ||

- | C30: Learning to Repeat: Fine Grained Action Repetition for Deep Reinforcement Learning\\ | + | C30: Zoneout: Regularizing RNNs by Randomly Preserving Hidden Activations\\ |

C31: Learning to Play in a Day: Faster Deep Reinforcement Learning by Optimality Tightening\\ | C31: Learning to Play in a Day: Faster Deep Reinforcement Learning by Optimality Tightening\\ | ||

C32: Learning Visual Servoing with Deep Features and Trust Region Fitted Q-Iteration\\ | C32: Learning Visual Servoing with Deep Features and Trust Region Fitted Q-Iteration\\ | ||

C33: An Actor-Critic Algorithm for Sequence Prediction\\ | C33: An Actor-Critic Algorithm for Sequence Prediction\\ |