ICLR 2017 论文列表
5th International Conference on Learning Representations, ICLR 2017, Toulon, France, April 24-26, 2017, Workshop Track Proceedings.
|
CommAI: Evaluating the first steps towards a useful general AI.
Towards "AlphaChem": Chemical Synthesis Planning with Tree Search and Deep Neural Network Policies.
Early Methods for Detecting Adversarial Images.
Variational Reference Priors.
REBAR: Low-variance, unbiased gradient estimates for discrete latent variable models.
Compact Embedding of Binary-coded Inputs and Outputs using Bloom Filters.
Adversarial Examples for Semantic Image Segmentation.
Arbitrary Style Transfer in Real-time with Adaptive Instance Normalization.
Precise Recovery of Latent Vectors from Generative Adversarial Networks.
Regularizing Neural Networks by Penalizing Confident Output Distributions.
Transferring Knowledge to Smaller Network with Class-Distance Loss.
Coupling Distributed and Symbolic Execution for Natural Language Queries.
Revisiting Batch Normalization For Practical Domain Adaptation.
The High-Dimensional Geometry of Binary Neural Networks.
Delving into adversarial attacks on deep policies.
Neurogenesis-Inspired Dictionary Learning: Online Model Adaption in a Changing World.
Trace Norm Regularised Deep Multi-Task Learning.
Shake-Shake regularization of 3-branch residual networks.
Factorization tricks for LSTM networks.
Fast Generation for Convolutional Autoregressive Models.
On Improving the Numerical Stability of Winograd Convolutions.
Online Multi-Task Learning Using Active Sampling.
Pl@ntNet app in the era of deep learning.
Dance Dance Convolution.
Neu0.
Training Triplet Networks with GAN.
Joint Multimodal Learning with Deep Generative Models.
The Preimage of Rectifier Network Activities.
Synthetic Gradient Methods with Virtual Forward-Backward Networks.
A Smooth Optimisation Perspective on Training Feedforward Neural Networks.
Emergence of Language with Multi-agent Games: Learning to Communicate with Sequences of Symbols.
Efficient variational Bayesian neural network ensembles for outlier detection.
Fast Adaptation in Generative Models with Generative Matching Networks.
Unsupervised Feature Learning for Audio Analysis.
Variational Intrinsic Control.
Playing SNES in the Retro Learning Environment.
Embracing Data Abundance.
Restricted Boltzmann Machines provide an accurate metric for retinal responses to visual stimuli.
Encoding and Decoding Representations with Sum- and Max-Product Networks.
Deep Kernel Machines via the Kernel Reparametrization Trick.
Training a Subsampling Mechanism in Expectation.
Explaining the Learning Dynamics of Direct Feedback Alignment.
DeepCloak: Masking Deep Neural Network Models for Robustness Against Adversarial Samples.
Understanding intermediate layers using linear classifier probes.
Generative Adversarial Learning of Markov Chains.
Performance guarantees for transferring representations.
Char2Wav: End-to-End Speech Synthesis.
Efficient Sparse-Winograd Convolutional Neural Networks.
Changing Model Behavior at Test-time Using Reinforcement Learning.
Adversarial Discriminative Domain Adaptation (workshop extended abstract).
Unseen Style Transfer Based on a Conditional Fast Style Transfer Network.
Memory Matching Networks for Genomic Sequence Classification.
Out-of-class novelty generation: an experimental foundation.
De novo drug design with deep generative models : an empirical study.
Loss is its own Reward: Self-Supervision for Reinforcement Learning.
Natural Language Generation in Dialogue using Lexicalized and Delexicalized Data.
Particle Value Functions.
Joint Training of Ratings and Reviews with Recurrent Recommender Networks.
Tactics of Adversarial Attack on Deep Reinforcement Learning Agents.
Joint Embeddings of Scene Graphs and Images.
Semantic embeddings for program behaviour patterns.
Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results.
Audio Super-Resolution using Neural Networks.
Adversarial Attacks on Neural Network Policies.
On Hyperparameter Optimization in Learning Systems.
Neural Expectation Maximization.
Neural Combinatorial Optimization with Reinforcement Learning.
Robustness to Adversarial Examples through an Ensemble of Specialists.
Accelerating Eulerian Fluid Simulation With Convolutional Networks.
Accelerating SGD for Distributed Deep-Learning Using an Approximted Hessian Matrix.
Unsupervised and Scalable Algorithm for Learning Node Representations.
Reinterpreting Importance-Weighted Autoencoders.
Learning Algorithms for Active Learning.
Intelligent synapses for multi-task and transfer learning.
Deep Nets Don't Learn via Memorization.
Forced to Learn: Discovering Disentangled Representations Without Exhaustive Labels.
The Effectiveness of Transfer Learning in Electronic Health Records Data.
Compositional Kernel Machines.
Charged Point Normalization: An Efficient Solution to the Saddle Point Problem.
Gated Multimodal Units for Information Fusion.
Song From PI: A Musically Plausible Network for Pop Music Generation.
Development of JavaScript-based deep learning platform and application to distributed training.
Adversarial examples in the physical world.
Perception Updating Networks: On architectural constraints for interpretable video generative models.
Generalizable Features From Unsupervised Learning.
Tuning Recurrent Neural Networks with Reinforcement Learning.
RenderGAN: Generating Realistic Labeled Data.
Recurrent Normalization Propagation.
Automated Generation of Multilingual Clusters for the Evaluation of Distributed Representations.
A Differentiable Physics Engine for Deep Learning in Robotics.
Learning to Discover Sparse Graphical Models.
Multiplicative LSTM for sequence modelling.
Discovering objects and their relations from entangled scene representations.
Deep Learning with Sets and Point Clouds.
Online Structure Learning for Sum-Product Networks with Gaussian Leaves.
Bit-Pragmatic Deep Neural Network Computing.
Exponential Machines.
On Robust Concepts and Small Neural Nets.
Lifelong Perceptual Programming By Example.
Neural Functional Programming.
Dataset Augmentation in Feature Space.
Unsupervised Perceptual Rewards for Imitation Learning.
Symmetry-Breaking Convergence Analysis of Certain Two-layered Neural Networks with ReLU nonlinearity.
Short and Deep: Sketching and Neural Networks.
Fast Chirplet Transform Injects Priors in Deep Learning of Animal Calls and Speech.
Towards an automatic Turing test: Learning to evaluate dialogue responses.
Extrapolation and learning equations.
Programming With a Differentiable Forth Interpreter.
Adaptive Feature Abstraction for Translating Video to Language.
Semi-supervised deep learning by metric embedding.
A Theoretical Framework for Robustness of (Deep) Classifiers against Adversarial Samples.
