作者
Yoshua Bengio
Machine Learning
Systematic Evaluation of Causal Discovery in Visual Model Based Reinforcement Learning
Variational Causal Networks: Approximate Bayesian Inference over Causal Structures
Comments 10 pages, 6 figures
SpeechBrain: A General-Purpose Speech Toolkit
Comments Preprint
Parameterizing Branch-and-Bound Search Trees to Learn Branching Policies
Comments AAAI 2021 camera-ready version with supplementary materials, improved readability of figures in main article. Code, data and trained models are available at https://github.com/ds4dm/branch-search-trees
Journal ref Proceedings of the AAAI Conference on Artificial Intelligence 2021, 35(5), 3931-3939
Fast and Slow Learning of Recurrent Independent Mechanisms
Comments Accepted at ICLR'21
Comparative Study of Learning Outcomes for Online Learning Platforms
Comments 14 pages, 3 figures, 2 tables, accepted at AIED 2021 (2021 Conference on Artificial Intelligence in Education)
Learning Neural Generative Dynamics for Molecular Conformation Generation
Comments Accepted by ICLR 2021. Code is available at \url{https://github.com/DeepGraphLearning/CGCF-ConfGen}
Transformers with Competitive Ensembles of Independent Mechanisms
Comments Under Review, ICML 2021
An Analysis of the Adaptation Speed of Causal Models
Comments Published at AISTATS 2021. 10 pages main articles, 19 pages supplement, 10 figures
Towards Causal Representation Learning
Comments Special Issue of Proceedings of the IEEE - Advances in Machine Learning and Deep Neural Networks
Saliency is a Possible Red Herring When Diagnosing Poor Generalization
Comments 25 pages, 27 figures, 5 tables, code in paper (https://github.com/josephdviviano/saliency-red-herring). Published at International Conference on Learning Representations (ICLR) 2021. Previously titled "Underwhelming Generalization Improvements from Controlling Feature Attribution"
Cross-Modal Information Maximization for Medical Imaging: CMIM
Comments ICASSP 2021
Scaling Equilibrium Propagation to Deep ConvNets by Drastically Reducing its Gradient Estimator Bias
Comments NeurIPS 2020 Workshop : "Beyond Backpropagation Novel Ideas for Training Neural Architectures". arXiv admin note: substantial text overlap with arXiv:2006.03824
Deep Verifier Networks: Verification of Deep Discriminative Models with Deep Generative Models
Comments Accepted to AAAI 2021
Meta-learning framework with applications to zero-shot time-series forecasting
On the Learning Dynamics of Deep Neural Networks
Comments 19 pages, 7 figures
Untangling tradeoffs between recurrence and self-attention in neural networks
Machine Learning for Glacier Monitoring in the Hindu Kush Himalaya
Comments Accepted for a spotlight talk and a poster at the Tackling Climate Change with Machine Learning workshop at NeurIPS 2020
Object-Centric Image Generation from Layouts
Comments AAAI 2021
Joint Learning of Generative Translator and Classifier for Visually Similar Classes
Comments 14 pages, 17 figures, 13 tables
RetroGNN: Approximating Retrosynthesis by Graph Neural Networks for De Novo Drug Design
Comments Machine Learning for Molecules Workshop at NeurIPS 2020
CausalWorld: A Robotic Manipulation Benchmark for Causal Structure and Transfer Learning
Comments The first two authors contributed equally, the last two authors avised jointly
Recurrent Independent Mechanisms
Learning to Combine Top-Down and Bottom-Up Signals in Recurrent Neural Networks with Attention over Modules
Comments ICML 2020
Object Files and Schemata: Factorizing Declarative and Procedural Knowledge in Dynamical Systems
Comments Type/Token Distinction in Deep learning Framework
Unsupervised State Representation Learning in Atari
Comments NeurIPS 2019; v6 fixes a broken figure reference
Experience Grounds Language
Comments Empirical Methods in Natural Language Processing (EMNLP), 2020
