Skip to main content


Past events

March 20, 2023
Interpreting Training
Speaker: Naomi Saphra

March 10, 2023
A Data-Centric View on Reliable Generalization: From ImageNet to LAION-5B
Speaker: Ludwig Schmidt

February 27, 2023
Natural Inductive Biases for Artificial Intelligence
Speaker: Thomas Keller

February 27, 2023
Beyond Bayes: towards new principles of optimality for neuroscience and AI
Speaker: Richard Lange

February 27, 2023
Towards Human-like Deep Reinforcement Learning
Speaker: Willa Carvalho

February 24, 2023
Neural networks make stuff up. What should we do about it?
Speaker: Chelsea Finn

February 10, 2023
Studying Neural Net Generalization through Influence Functions
Speaker: Roger Grosse

February 3, 2023
Data structure and curse of dimensionality in deep learning
Speaker: Matthieu Wyart0