On Adversarial Mixup Resynthesis
Comments 'Camera-ready draft'
作者
Yoshua Bengio
Machine Learning
Establishing an Evaluation Metric to Quantify Climate Change Image Realism
Comments Accepted to the NeurIPS 2019 Workshop, Tackling Climate Change with Machine Learning
Icentia11K: An Unsupervised Representation Learning Dataset for Arrhythmia Subtype Discovery
Comments Under Review
Predicting ice flow using machine learning
Comments 33rd Conference on Neural Information Processing Systems (NeurIPS), Workshop on Tackling Climate Change with Machine Learning, Vancouver, Canada, 2019
Variational Temporal Abstraction
Comments Accepted in NeurIPS 2019
The Benefits of Over-parameterization at Initialization in Deep ReLU Networks
Avoidance Learning Using Observational Reinforcement Learning
Tell, Draw, and Repeat: Generating and Modifying Images Based on Continual Linguistic Instruction
Comments Accepted at ICCV 2019
Journal ref Proceedings of the 2019 IEEE International Conference on Computer Vision (ICCV)
Torchmeta: A Meta-Learning library for PyTorch
Towards Training Recurrent Neural Networks for Lifelong Learning
Comments Accepted at Neural Computation
Data-Driven Approach to Encoding and Decoding 3-D Crystal Structures
Learning Fixed Points in Generative Adversarial Networks: From Image-to-Image Translation to Disease Detection and Localization
Interactive Language Learning by Question Answering
Comments EMNLP 2019
Reinforced Imitation in Heterogeneous Action Space
Comments The extended version of the work "Reinforced Imitation Learning from Observations" presented on the NeurIPS workshop "Imitation Learning and its Challenges in Robotics"
Interpretable Convolutional Filters with SincNet
Comments In Proceedings of NIPS@IRASL 2018. arXiv admin note: substantial text overlap with arXiv:1808.00158
Speaker Recognition from Raw Waveform with SincNet
Comments In Proceedings of SLT 2018
GradMask: Reduce Overfitting by Regularizing Saliency
Do Neural Dialog Systems Use the Conversation History Effectively? An Empirical Study
Comments To appear at ACL 2019(oral; nominated for best paper)
Speech Model Pre-training for End-to-End Spoken Language Understanding
Comments Accepted to Interspeech 2019
Depth with Nonlinearity Creates No Bad Local Minima in ResNets
Journal ref Neural Networks, volume 118, pages 167-174 (2019)
Weakly-supervised Knowledge Graph Alignment with Adversarial Learning
Learning the Arrow of Time
Comments A shorter version of this work was presented at the Theoretical Phyiscs for Deep Learning Workshop, ICML 2019
Reinforcement Learning with Competitive Ensembles of Information-Constrained Primitives
Comments Preprint, Under Review
Conditional Computation for Continual Learning
Comments NeurIPS 2018 Continual Learning Workshop
Learning Powerful Policies by Using Consistent Dynamics Model
Comments Accpted at RLDM 2019
InfoMask: Masked Variational Latent Representation to Localize Chest Disease
Comments Accepted to MICCAI 2019
Updates of Equilibrium Prop Match Gradients of Backprop Through Time in an RNN with Static Input
On the Spectral Bias of Neural Networks
Comments 23 pages
Journal ref ICML 2019
Attention Based Pruning for Shift Networks
State-Reification Networks: Improving Generalization by Modeling the Distribution of Hidden Representations
Comments ICML 2019 [full oral]. arXiv admin note: text overlap with arXiv:1805.08394
