ICLR 2017

This is an old revision of the document!

Workshop Poster Sessions

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.

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

  1. Extrapolation and learning equations
  2. Effectiveness of Transfer Learning in EHR data
  3. Intelligent synapses for multi-task and transfer learning
  4. Unsupervised and Efficient Neural Graph Model with Distributed Representations
  5. Accelerating SGD for Distributed Deep-Learning Using an Approximted Hessian Matrix
  6. Accelerating Eulerian Fluid Simulation With Convolutional Networks
  7. Forced to Learn: Discovering Disentangled Representations Without Exhaustive Labels
  8. Deep Nets Don't Learn via Memorization
  9. Learning Algorithms for Active Learning
  10. Reinterpreting Importance-Weighted Autoencoders
  11. Robustness to Adversarial Examples through an Ensemble of Specialists
  12. Neural Expectation Maximization
  13. On Hyperparameter Optimization in Learning Systems
  14. Recurrent Normalization Propagation
  15. Joint Training of Ratings and Reviews with Recurrent Recommender Networks
  16. Towards an Automatic Turing Test: Learning to Evaluate Dialogue Responses
  17. Joint Embeddings of Scene Graphs and Images
  18. Unseen Style Transfer Based on a Conditional Fast Style Transfer Network

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

  1. Audio Super-Resolution using Neural Networks
  2. Semantic embeddings for program behaviour patterns
  3. De novo drug design with deep generative models : an empirical study
  4. Memory Matching Networks for Genomic Sequence Classification
  5. Char2Wav: End-to-End Speech Synthesis
  6. Fast Chirplet Transform Injects Priors in Deep Learning of Animal Calls and Speech
  7. Weight-averaged consistency targets improve semi-supervised deep learning results
  8. Particle Value Functions
  9. Out-of-class novelty generation: an experimental foundation
  10. Performance guarantees for transferring representations
  11. Generative Adversarial Learning of Markov Chains
  12. Short and Deep: Sketching and Neural Networks
  13. Understanding intermediate layers using linear classifier probes
  14. Symmetry-Breaking Convergence Analysis of Certain Two-layered Neural Networks with ReLU nonlinearity
  15. Neural Combinatorial Optimization with Reinforcement Learning
  16. Tactics of Adversarial Attacks on Deep Reinforcement Learning Agents
  17. Adversarial Discriminative Domain Adaptation (workshop extended abstract)
  18. Efficient Sparse-Winograd Convolutional Neural Networks

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

  1. Programming With a Differentiable Forth Interpreter
  2. Unsupervised Feature Learning for Audio Analysis
  3. Neural Functional Programming
  4. A Smooth Optimisation Perspective on Training Feedforward Neural Networks
  5. Synthetic Gradient Methods with Virtual Forward-Backward Networks
  6. Explaining the Learning Dynamics of Direct Feedback Alignment
  7. Training a Subsampling Mechanism in Expectation
  8. Deep Kernel Machines via the Kernel Reparametrization Trick
  9. Encoding and Decoding Representations with Sum- and Max-Product Networks
  10. Embracing Data Abundance
  11. Variational Intrinsic Control
  12. Fast Adaptation in Generative Models with Generative Matching Networks
  13. Efficient variational Bayesian neural network ensembles for outlier detection
  14. Emergence of Language with Multi-agent Games: Learning to Communicate with Sequences of Symbols
  15. Adaptive Feature Abstraction for Translating Video to Language
  16. Delving into adversarial attacks on deep policies
  17. Tuning Recurrent Neural Networks with Reinforcement Learning
  18. DeepMask: Masking DNN Models for robustness against adversarial samples
  19. Restricted Boltzmann Machines provide an accurate metric for retinal responses to visual stimuli

Tuesday Afternoon (April 25th, 4:30pm to 6:30pm)

  1. Lifelong Perceptual Programming By Example
  2. Neu0
  3. Dance Dance Convolution
  4. Bit-Pragmatic Deep Neural Network Computing
  5. On Improving the Numerical Stability of Winograd Convolutions
  6. Fast Generation for Convolutional Autoregressive Models
  8. Training Triplet Networks with GAN
  9. On Robust Concepts and Small Neural Nets
  10. Pl@ntNet app in the era of deep learning
  11. Exponential Machines
  12. Online Multi-Task Learning Using Biased Sampling
  13. Online Structure Learning for Sum-Product Networks with Gaussian Leaves
  14. A Theoretical Framework for Robustness of (Deep) Classifiers against Adversarial Samples
  15. Compositional Kernel Machines
  16. Loss is its own Reward: Self-Supervision for Reinforcement Learning
  17. Changing Model Behavior at Test-time Using Reinforcement Learning
  18. Precise Recovery of Latent Vectors from Generative Adversarial Networks
  19. Arbitrary Style Transfer in Real-time with Adaptive Instance Normalization

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

  2. The High-Dimensional Geometry of Binary Neural Networks
  3. Discovering objects and their relations from entangled scene representations
  4. A Differentiable Physics Engine for Deep Learning in Robotics
  5. Automated Generation of Multilingual Clusters for the Evaluation of Distributed Representations
  6. Development of JavaScript-based deep learning platform and application to distributed training
  7. Factorization tricks for LSTM networks
  8. Shake-Shake regularization of 3-branch residual networks
  9. Trace Norm Regularised Deep Multi-Task Learning
  10. Deep Learning with Sets and Point Clouds
  11. Dataset Augmentation in Feature Space
  12. Multiplicative LSTM for sequence modelling
  13. Learning to Discover Sparse Graphical Models
  14. Revisiting Batch Normalization For Practical Domain Adaptation
  15. Early Methods for Detecting Adversarial Images and a Colorful Saliency Map
  16. Natural Language Generation in Dialogue using Lexicalized and Delexicalized Data
  17. Coupling Distributed and Symbolic Execution for Natural Language Queries
  18. Adversarial Examples for Semantic Image Segmentation
  19. RenderGAN: Generating Realistic Labeled Data

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

  1. Song From PI: A Musically Plausible Network for Pop Music Generation
  2. Charged Point Normalization: An Efficient Solution to the Saddle Point Problem
  3. Towards “AlphaChem”: Chemical Synthesis Planning with Tree Search and Deep Neural Network Policies
  4. CommAI: Evaluating the first steps towards a useful general AI
  5. Joint Multimodal Learning with Deep Generative Models
  6. Transferring Knowledge to Smaller Network with Class-Distance Loss
  7. Regularizing Neural Networks by Penalizing Confident Output Distributions
  8. Adversarial Attacks on Neural Network Policies
  9. Generalizable Features From Unsupervised Learning
  10. Compact Embedding of Binary-coded Inputs and Outputs using Bloom Filters
  11. Semi-supervised deep learning by metric embedding
  12. REBAR: Low-variance, unbiased gradient estimates for discrete latent variable models
  13. Variational Reference Priors
  14. Gated Multimodal Units for Information Fusion
  15. Playing SNES in the Retro Learning Environment
  16. Unsupervised Perceptual Rewards for Imitation Learning
  17. Perception Updating Networks: On architectural constraints for interpretable video generative models
  18. Adversarial examples in the physical world