作者
Yoshua Bengio
Machine Learning
A General Purpose Neural Architecture for Geospatial Systems
Comments Presented at AI + HADR Workshop at NeurIPS 2022
Consistent Training via Energy-Based GFlowNets for Modeling Discrete Joint Distributions
Comments 9 Pages, 10 Figures
Discrete Factorial Representations as an Abstraction for Goal Conditioned Reinforcement Learning
Comments Neurips 2022
FL Games: A Federated Learning Framework for Distribution Shifts
Comments Accepted as ORAL at NeurIPS Workshop on Federated Learning: Recent Advances and New Challenges. arXiv admin note: text overlap with arXiv:2205.11101
Temporal Latent Bottleneck: Synthesis of Fast and Slow Processing Mechanisms in Sequence Learning
Neural Attentive Circuits
Comments To appear at NeurIPS 2022
Interpolated Adversarial Training: Achieving Robust Neural Networks without Sacrificing Too Much Accuracy
Comments This is the latest version, which is published in the Journal, "Neural Networks", in 2022. All the previous results are unchanged. First two authors contributed equally
Journal ref Neural Networks, volume 154, pages 218-233 (2022)
Interpolation Consistency Training for Semi-Supervised Learning
Comments This is the latest version, which is published in the Journal, "Neural Networks", in 2022. All the previous results are unchanged. Keyword: Deep Learning, Semi-supervised Learning, Mixup
Journal ref Neural Networks, volume 145, pages 90-106 (2022)
Robust and Controllable Object-Centric Learning through Energy-based Models
MAgNet: Mesh Agnostic Neural PDE Solver
Generative Augmented Flow Networks
The Causal-Neural Connection: Expressiveness, Learnability, and Inference
Comments 10 pages main body (53 total pages with references and appendix), 5 figures in main body (20 total figures including appendix)
Graph-Based Active Machine Learning Method for Diverse and Novel Antimicrobial Peptides Generation and Selection
Comments Under Review at Sciences Advances
Designing Biological Sequences via Meta-Reinforcement Learning and Bayesian Optimization
AI for Global Climate Cooperation: Modeling Global Climate Negotiations, Agreements, and Long-Term Cooperation in RICE-N
Comments 12 pages (21 with appendices), 5 figures. For associated working group, see https://www.ai4climatecoop.org/
Diversifying Design of Nucleic Acid Aptamers Using Unsupervised Machine Learning
Inductive Biases for Deep Learning of Higher-Level Cognition
Comments This document contains a review of authors research as part of the requirement of AG's predoctoral exam, an overview of the main contributions of the authors few recent papers (co-authored with several other co-authors) as well as a vision of proposed future research
Bayesian Structure Learning with Generative Flow Networks
Your Autoregressive Generative Model Can be Better If You Treat It as an Energy-Based One
Comments Preprint version
On Neural Architecture Inductive Biases for Relational Tasks
On the Generalization and Adaption Performance of Causal Models
ClimateGAN: Raising Climate Change Awareness by Generating Images of Floods
Journal ref ICLR 2022
Generative Flow Networks for Discrete Probabilistic Modeling
Comments Accepted by ICML 2022
Predicting Tactical Solutions to Operational Planning Problems under Imperfect Information
Comments Same as arXiv:1807.11876, added by mistake
Journal ref INFORMS Journal on Computing 34(1):227-242, 2021
Predicting Tactical Solutions to Operational Planning Problems under Imperfect Information
Journal ref INFORMS Journal on Computing 34(1):227-242, 2021
Building Robust Ensembles via Margin Boosting
Comments Accepted by ICML 2022
