257 citations · 508 across the 16 of their papers we have counts for
16 papers
Coordination Among Neural Modules Through a Shared Global Workspace
Anirudh Goyal, Aniket Didolkar, Alex Lamb +7
Deep learning has seen a movement away from representing examples with a monolithic hidden state towards a richly structured state. For example, Transformers segment by position, a…
Reinforcement Learning with Random Delays
Simon Ramstedt, Yann Bouteiller, Giovanni Beltrame +2
Action and observation delays commonly occur in many Reinforcement Learning applications, such as remote control scenarios. We study the anatomy of randomly delayed environments, a…
DDD20 End-to-End Event Camera Driving Dataset: Fusing Frames and Events with Deep Learning for Improved Steering Prediction
Yuhuang Hu, Jonathan Binas, Daniel Neil +2
Neuromorphic event cameras are useful for dynamic vision problems under difficult lighting conditions. To enable studies of using event cameras in automobile driving applications,…
Out-of-Distribution Generalization via Risk Extrapolation (REx)
David Krueger, Ethan Caballero, Joern-Henrik Jacobsen +5
Distributional shift is one of the major obstacles when transferring machine learning prediction systems from the lab to the real world. To tackle this problem, we assume that vari…
Reinforcement Learning with Competitive Ensembles of Information-Constrained Primitives
Anirudh Goyal, Shagun Sodhani, Jonathan Binas +3
Reinforcement learning agents that operate in diverse and complex environments can benefit from the structured decomposition of their behavior. Often, this is addressed in the cont…
State-Reification Networks: Improving Generalization by Modeling the Distribution of Hidden Representations
Alex Lamb, Jonathan Binas, Anirudh Goyal +5
Machine learning promises methods that generalize well from finite labeled data. However, the brittleness of existing neural net approaches is revealed by notable failures, such as…