# Differences

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

iclr2017:workshop_posters [2017/03/28 08:20] rnogueira |
iclr2017:workshop_posters [2017/04/23 09:27] (current) hugo |
||
---|---|---|---|

Line 3: | Line 3: | ||

Below are the Workshop 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 Workshop Track. | Below are the Workshop 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 Workshop 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> | ||

====Monday Morning (April 24th, 10:30am to 12:30pm)==== | ====Monday Morning (April 24th, 10:30am to 12:30pm)==== | ||

- | - Extrapolation and learning equations | + | W1: Extrapolation and learning equations\\ |

- | - Effectiveness of Transfer Learning in EHR data | + | W2: Effectiveness of Transfer Learning in EHR data\\ |

- | - Intelligent synapses for multi-task and transfer learning | + | W3: Intelligent synapses for multi-task and transfer learning\\ |

- | - Unsupervised and Efficient Neural Graph Model with Distributed Representations | + | W4: Unsupervised and Efficient Neural Graph Model with Distributed Representations\\ |

- | - Accelerating SGD for Distributed Deep-Learning Using an Approximted Hessian Matrix | + | W5: Accelerating SGD for Distributed Deep-Learning Using an Approximted Hessian Matrix\\ |

- | - Accelerating Eulerian Fluid Simulation With Convolutional Networks | + | W6: Accelerating Eulerian Fluid Simulation With Convolutional Networks\\ |

- | - Forced to Learn: Discovering Disentangled Representations Without Exhaustive Labels | + | W7: Forced to Learn: Discovering Disentangled Representations Without Exhaustive Labels\\ |

- | - Deep Nets Don't Learn via Memorization | + | W8: Dataset Augmentation in Feature Space\\ |

- | - Learning Algorithms for Active Learning | + | W9: Learning Algorithms for Active Learning\\ |

- | - Reinterpreting Importance-Weighted Autoencoders | + | W10: Reinterpreting Importance-Weighted Autoencoders\\ |

- | - Robustness to Adversarial Examples through an Ensemble of Specialists | + | W11: Robustness to Adversarial Examples through an Ensemble of Specialists\\ |

- | - Neural Expectation Maximization | + | W12: (empty) \\ |

- | - On Hyperparameter Optimization in Learning Systems | + | W13: On Hyperparameter Optimization in Learning Systems\\ |

- | - Recurrent Normalization Propagation | + | W14: Recurrent Normalization Propagation\\ |

- | - Joint Training of Ratings and Reviews with Recurrent Recommender Networks | + | W15: Joint Training of Ratings and Reviews with Recurrent Recommender Networks\\ |

- | - Towards an Automatic Turing Test: Learning to Evaluate Dialogue Responses | + | W16: Towards an Automatic Turing Test: Learning to Evaluate Dialogue Responses\\ |

- | - Joint Embeddings of Scene Graphs and Images | + | W17: Joint Embeddings of Scene Graphs and Images\\ |

- | - Unseen Style Transfer Based on a Conditional Fast Style Transfer Network | + | W18: Unseen Style Transfer Based on a Conditional Fast Style Transfer Network\\ |

+ | |||

+ | <html><div id='monday_afternoon'></div></html> | ||

====Monday Afternoon (April 24th, 4:30pm to 6:30pm)==== | ====Monday Afternoon (April 24th, 4:30pm to 6:30pm)==== | ||

- | - Audio Super-Resolution using Neural Networks | + | W1: Audio Super-Resolution using Neural Networks\\ |

- | - Semantic embeddings for program behaviour patterns | + | W2: Semantic embeddings for program behaviour patterns\\ |

- | - De novo drug design with deep generative models : an empirical study | + | W3: De novo drug design with deep generative models : an empirical study\\ |

- | - Memory Matching Networks for Genomic Sequence Classification | + | W4: Memory Matching Networks for Genomic Sequence Classification\\ |

- | - Char2Wav: End-to-End Speech Synthesis | + | W5: Char2Wav: End-to-End Speech Synthesis\\ |

- | - Fast Chirplet Transform Injects Priors in Deep Learning of Animal Calls and Speech | + | W6: Fast Chirplet Transform Injects Priors in Deep Learning of Animal Calls and Speech\\ |

- | - Weight-averaged consistency targets improve semi-supervised deep learning results | + | W7: Weight-averaged consistency targets improve semi-supervised deep learning results\\ |

- | - Particle Value Functions | + | W8: Particle Value Functions\\ |

- | - Out-of-class novelty generation: an experimental foundation | + | W9: Out-of-class novelty generation: an experimental foundation\\ |

- | - Performance guarantees for transferring representations | + | W10: Performance guarantees for transferring representations\\ |

- | - Generative Adversarial Learning of Markov Chains | + | W11: Generative Adversarial Learning of Markov Chains\\ |

- | - Short and Deep: Sketching and Neural Networks | + | W12: Short and Deep: Sketching and Neural Networks\\ |

- | - Understanding intermediate layers using linear classifier probes | + | W13: Understanding intermediate layers using linear classifier probes\\ |

- | - Symmetry-Breaking Convergence Analysis of Certain Two-layered Neural Networks with ReLU nonlinearity | + | W14: Symmetry-Breaking Convergence Analysis of Certain Two-layered Neural Networks with ReLU nonlinearity\\ |

- | - Neural Combinatorial Optimization with Reinforcement Learning | + | W15: Neural Combinatorial Optimization with Reinforcement Learning\\ |

- | - Tactics of Adversarial Attacks on Deep Reinforcement Learning Agents | + | W16: Tactics of Adversarial Attacks on Deep Reinforcement Learning Agents\\ |

- | - Adversarial Discriminative Domain Adaptation (workshop extended abstract) | + | W17: Adversarial Discriminative Domain Adaptation (workshop extended abstract)\\ |

- | - Efficient Sparse-Winograd Convolutional Neural Networks | + | W18: Efficient Sparse-Winograd Convolutional Neural Networks\\ |

+ | W19: Neural Expectation Maximization\\ | ||

+ | <html><div id='tuesday_morning'></div></html> | ||

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

- | - Programming With a Differentiable Forth Interpreter | + | W1: Programming With a Differentiable Forth Interpreter\\ |

- | - Unsupervised Feature Learning for Audio Analysis | + | W2: Unsupervised Feature Learning for Audio Analysis\\ |

- | - Neural Functional Programming | + | W3: Neural Functional Programming\\ |

- | - A Smooth Optimisation Perspective on Training Feedforward Neural Networks | + | W4: A Smooth Optimisation Perspective on Training Feedforward Neural Networks\\ |

- | - Synthetic Gradient Methods with Virtual Forward-Backward Networks | + | W5: Synthetic Gradient Methods with Virtual Forward-Backward Networks\\ |

- | - Explaining the Learning Dynamics of Direct Feedback Alignment | + | W6: Explaining the Learning Dynamics of Direct Feedback Alignment\\ |

- | - Training a Subsampling Mechanism in Expectation | + | W7: Training a Subsampling Mechanism in Expectation\\ |

- | - Deep Kernel Machines via the Kernel Reparametrization Trick | + | W8: Deep Kernel Machines via the Kernel Reparametrization Trick\\ |

- | - Encoding and Decoding Representations with Sum- and Max-Product Networks | + | W9: Encoding and Decoding Representations with Sum- and Max-Product Networks\\ |

- | - Embracing Data Abundance | + | W10: Embracing Data Abundance\\ |

- | - Variational Intrinsic Control | + | W11: Variational Intrinsic Control\\ |

- | - Fast Adaptation in Generative Models with Generative Matching Networks | + | W12: Fast Adaptation in Generative Models with Generative Matching Networks\\ |

- | - Efficient variational Bayesian neural network ensembles for outlier detection | + | W13: Efficient variational Bayesian neural network ensembles for outlier detection\\ |

- | - Emergence of Language with Multi-agent Games: Learning to Communicate with Sequences of Symbols | + | W14: Emergence of Language with Multi-agent Games: Learning to Communicate with Sequences of Symbols\\ |

- | - Adaptive Feature Abstraction for Translating Video to Language | + | W15: Adaptive Feature Abstraction for Translating Video to Language\\ |

- | - Delving into adversarial attacks on deep policies | + | W16: Delving into adversarial attacks on deep policies\\ |

- | - Tuning Recurrent Neural Networks with Reinforcement Learning | + | W17: Tuning Recurrent Neural Networks with Reinforcement Learning\\ |

- | - DeepMask: Masking DNN Models for robustness against adversarial samples | + | W18: DeepMask: Masking DNN Models for robustness against adversarial samples\\ |

- | - Restricted Boltzmann Machines provide an accurate metric for retinal responses to visual stimuli | + | W19: Restricted Boltzmann Machines provide an accurate metric for retinal responses to visual stimuli\\ |

- | ====Tuesday Afternoon (April 25th, 4:30pm to 6:30pm)==== | + | <html><div id='tuesday_afternoon'></div></html> |

- | - Lifelong Perceptual Programming By Example | + | ====Tuesday Afternoon (April 25th, 2:00pm to 4:00pm)==== |

- | - Neu0 | + | W1: Lifelong Perceptual Programming By Example\\ |

- | - Dance Dance Convolution | + | W2: Neu0\\ |

- | - Bit-Pragmatic Deep Neural Network Computing | + | W3: Dance Dance Convolution\\ |

- | - On Improving the Numerical Stability of Winograd Convolutions | + | W4: Bit-Pragmatic Deep Neural Network Computing\\ |

- | - Fast Generation for Convolutional Autoregressive Models | + | W5: On Improving the Numerical Stability of Winograd Convolutions\\ |

- | - THE PREIMAGE OF RECTIFIER NETWORK ACTIVITIES | + | W6: Fast Generation for Convolutional Autoregressive Models\\ |

- | - Training Triplet Networks with GAN | + | W7: THE PREIMAGE OF RECTIFIER NETWORK ACTIVITIES\\ |

- | - On Robust Concepts and Small Neural Nets | + | W8: Training Triplet Networks with GAN\\ |

- | - Pl@ntNet app in the era of deep learning | + | W9: On Robust Concepts and Small Neural Nets\\ |

- | - Exponential Machines | + | W10: Pl@ntNet app in the era of deep learning\\ |

- | - Online Multi-Task Learning Using Biased Sampling | + | W11: Exponential Machines\\ |

- | - Online Structure Learning for Sum-Product Networks with Gaussian Leaves | + | W12: Online Multi-Task Learning Using Biased Sampling\\ |

- | - A Theoretical Framework for Robustness of (Deep) Classifiers against Adversarial Samples | + | W13: Online Structure Learning for Sum-Product Networks with Gaussian Leaves\\ |

- | - Compositional Kernel Machines | + | W14: A Theoretical Framework for Robustness of (Deep) Classifiers against Adversarial Samples\\ |

- | - Loss is its own Reward: Self-Supervision for Reinforcement Learning | + | W15: Compositional Kernel Machines\\ |

- | - Changing Model Behavior at Test-time Using Reinforcement Learning | + | W16: Loss is its own Reward: Self-Supervision for Reinforcement Learning\\ |

- | - Precise Recovery of Latent Vectors from Generative Adversarial Networks | + | W17: REBAR: Low-variance, unbiased gradient estimates for discrete latent variable models\\ |

- | - Arbitrary Style Transfer in Real-time with Adaptive Instance Normalization | + | W18: Precise Recovery of Latent Vectors from Generative Adversarial Networks\\ |

+ | W19: Arbitrary Style Transfer in Real-time with Adaptive Instance Normalization\\ | ||

+ | <html><div id='wednesday_morning'></div></html> | ||

====Wednesday Morning (April 26th, 10:30am to 12:30pm)==== | ====Wednesday Morning (April 26th, 10:30am to 12:30pm)==== | ||

- | - NEUROGENESIS-INSPIRED DICTIONARY LEARNING: ONLINE MODEL ADAPTION IN A CHANGING WORLD | + | W1: NEUROGENESIS-INSPIRED DICTIONARY LEARNING: ONLINE MODEL ADAPTION IN A CHANGING WORLD\\ |

- | - The High-Dimensional Geometry of Binary Neural Networks | + | W2: The High-Dimensional Geometry of Binary Neural Networks\\ |

- | - Discovering objects and their relations from entangled scene representations | + | W3: Discovering objects and their relations from entangled scene representations\\ |

- | - A Differentiable Physics Engine for Deep Learning in Robotics | + | W4: A Differentiable Physics Engine for Deep Learning in Robotics\\ |

- | - Automated Generation of Multilingual Clusters for the Evaluation of Distributed Representations | + | W5: Automated Generation of Multilingual Clusters for the Evaluation of Distributed Representations\\ |

- | - Development of JavaScript-based deep learning platform and application to distributed training | + | W6: Development of JavaScript-based deep learning platform and application to distributed training\\ |

- | - Factorization tricks for LSTM networks | + | W7: Factorization tricks for LSTM networks\\ |

- | - Shake-Shake regularization of 3-branch residual networks | + | W8: Shake-Shake regularization of 3-branch residual networks\\ |

- | - Trace Norm Regularised Deep Multi-Task Learning | + | W9: Trace Norm Regularised Deep Multi-Task Learning\\ |

- | - Deep Learning with Sets and Point Clouds | + | W10: Deep Learning with Sets and Point Clouds\\ |

- | - Dataset Augmentation in Feature Space | + | W11: Deep Nets Don't Learn via Memorization\\ |

- | - Multiplicative LSTM for sequence modelling | + | W12: Multiplicative LSTM for sequence modelling\\ |

- | - Learning to Discover Sparse Graphical Models | + | W13: Learning to Discover Sparse Graphical Models\\ |

- | - Revisiting Batch Normalization For Practical Domain Adaptation | + | W14: Revisiting Batch Normalization For Practical Domain Adaptation\\ |

- | - Early Methods for Detecting Adversarial Images and a Colorful Saliency Map | + | W15: Early Methods for Detecting Adversarial Images and a Colorful Saliency Map\\ |

- | - Natural Language Generation in Dialogue using Lexicalized and Delexicalized Data | + | W16: Natural Language Generation in Dialogue using Lexicalized and Delexicalized Data\\ |

- | - Coupling Distributed and Symbolic Execution for Natural Language Queries | + | W17: Coupling Distributed and Symbolic Execution for Natural Language Queries\\ |

- | - Adversarial Examples for Semantic Image Segmentation | + | W18: Adversarial Examples for Semantic Image Segmentation\\ |

- | - RenderGAN: Generating Realistic Labeled Data | + | W19: RenderGAN: Generating Realistic Labeled Data\\ |

+ | <html><div id='wednesday_afternoon'></div></html> | ||

====Wednesday Afternoon (April 26th, 4:30pm to 6:30pm)==== | ====Wednesday Afternoon (April 26th, 4:30pm to 6:30pm)==== | ||

- | - Song From PI: A Musically Plausible Network for Pop Music Generation | + | W1: Song From PI: A Musically Plausible Network for Pop Music Generation\\ |

- | - Charged Point Normalization: An Efficient Solution to the Saddle Point Problem | + | W2: Charged Point Normalization: An Efficient Solution to the Saddle Point Problem\\ |

- | - Towards "AlphaChem": Chemical Synthesis Planning with Tree Search and Deep Neural Network Policies | + | W3: Towards "AlphaChem": Chemical Synthesis Planning with Tree Search and Deep Neural Network Policies\\ |

- | - CommAI: Evaluating the first steps towards a useful general AI | + | W4: CommAI: Evaluating the first steps towards a useful general AI\\ |

- | - Joint Multimodal Learning with Deep Generative Models | + | W5: Joint Multimodal Learning with Deep Generative Models\\ |

- | - Transferring Knowledge to Smaller Network with Class-Distance Loss | + | W6: Transferring Knowledge to Smaller Network with Class-Distance Loss\\ |

- | - Regularizing Neural Networks by Penalizing Confident Output Distributions | + | W7: Regularizing Neural Networks by Penalizing Confident Output Distributions\\ |

- | - Adversarial Attacks on Neural Network Policies | + | W8: Adversarial Attacks on Neural Network Policies\\ |

- | - Generalizable Features From Unsupervised Learning | + | W9: Generalizable Features From Unsupervised Learning\\ |

- | - Compact Embedding of Binary-coded Inputs and Outputs using Bloom Filters | + | W10: Compact Embedding of Binary-coded Inputs and Outputs using Bloom Filters\\ |

- | - Semi-supervised deep learning by metric embedding | + | W11: Semi-supervised deep learning by metric embedding\\ |

- | - REBAR: Low-variance, unbiased gradient estimates for discrete latent variable models | + | W12: Changing Model Behavior at Test-time Using Reinforcement Learning\\ |

- | - Variational Reference Priors | + | W13: Variational Reference Priors\\ |

- | - Gated Multimodal Units for Information Fusion | + | W14: Gated Multimodal Units for Information Fusion\\ |

- | - Playing SNES in the Retro Learning Environment | + | W15: Playing SNES in the Retro Learning Environment\\ |

- | - Unsupervised Perceptual Rewards for Imitation Learning | + | W16: Unsupervised Perceptual Rewards for Imitation Learning\\ |

- | - Perception Updating Networks: On architectural constraints for interpretable video generative models | + | W17: Perception Updating Networks: On architectural constraints for interpretable video generative models\\ |

- | - Adversarial examples in the physical world | + | W18: Adversarial examples in the physical world\\ |