The Variational Bandwidth Bottleneck: Stochastic Evaluation on an Information Budget
Comments Published as a conference paper at ICLR 2020
作者
Yoshua Bengio
Machine Learning
Toward Trustworthy AI Development: Mechanisms for Supporting Verifiable Claims
Multi-task self-supervised learning for Robust Speech Recognition
Comments In Proc. of ICASSP 2020
Modeling Cloud Reflectance Fields using Conditional Generative Adversarial Networks
Comments Code is available on Github: https://github.com/krisrs1128/clouds_dist
On the interplay between noise and curvature and its effect on optimization and generalization
Comments Accepted to AISTATS 2020
Continuous Domain Adaptation with Variational Domain-Agnostic Feature Replay
Machine Learning for Combinatorial Optimization: a Methodological Tour d'Horizon
Neural Bayes: A Generic Parameterization Method for Unsupervised Representation Learning
N-BEATS: Neural basis expansion analysis for interpretable time series forecasting
HighRes-net: Recursive Fusion for Multi-Frame Super-Resolution of Satellite Imagery
Comments 15 pages, 5 figures
Combating False Negatives in Adversarial Imitation Learning
Comments This is an extended version of the student abstract published at 34th AAAI Conference on Artificial Intelligence
Using Simulated Data to Generate Images of Climate Change
Comments Proceeding ML-IRL workshop at ICLR 2020
Universal Successor Features for Transfer Reinforcement Learning
Learning from Learning Machines: Optimisation, Rules, and Social Norms
On the Morality of Artificial Intelligence
On the Relation Between the Sharpest Directions of DNN Loss and the SGD Step Length
Journal ref International Conference on Learning Representations (ICLR) 2019
BabyAI: A Platform to Study the Sample Efficiency of Grounded Language Learning
Comments Accepted at ICLR 2019
A learning-based algorithm to quickly compute good primal solutions for Stochastic Integer Programs
MelGAN: Generative Adversarial Networks for Conditional Waveform Synthesis
The effect of task and training on intermediate representations in convolutional neural networks revealed with modified RV similarity analysis
Comments 4 pages, 4 figures, Conference on Cognitive Computational Neuroscience 2019
The Consciousness Prior
Applying Knowledge Transfer for Water Body Segmentation in Peru
Comments 5 pages, 3 figures, 1 table, NeurIPS 2019 Workshop on Machine Learning for the Developing World
Automated curriculum generation for Policy Gradients from Demonstrations
Comments Accepted to Deep RL Workshop at NeurIPS 2019
Ghost Units Yield Biologically Plausible Backprop in Deep Neural Networks
An Empirical Study of Example Forgetting during Deep Neural Network Learning
Comments ICLR 2019
Tackling Climate Change with Machine Learning
Comments For additional resources, please visit the website that accompanies this paper: https://www.climatechange.ai/
Gradient based sample selection for online continual learning
Comments Neurips 2019
Small-GAN: Speeding Up GAN Training Using Core-sets
How to Initialize your Network? Robust Initialization for WeightNorm & ResNets
Comments First two authors have equal contribution
