Fall 2021

October 25, 2021

Learning to Walk with Rapid Motor Adaptation

Speaker: Jitendra Malik (Berkeley)

Event Recording:
Legged locomotion is commonly studied and programmed as a discrete set of structured gait patterns, like walk, trot, gallop.  However, studies of children learning to walk (Adolph et al) show that real-world locomotion is often quite...

November 8, 2021

Coordination and Decentralization in Provision of Social Services

Speaker: Rediet Abebe (Berkeley)

Poverty is a prevalent issue in the United States, impacting over twenty percent of the population. Given poverty's detrimental impact on communities, there is a pressing need to predict hardship as well as provide timely and effective...

November 15, 2021

Two F-Words in Peer Review (Fraud and Feedback)

Speaker: Nihar Shah (Carnegie Mellon University)

Event Recording:
In this talk, we present two major challenges in peer review, propose solutions with guarantees, and discuss important open problems. (1) Fraud: There have been several recent discoveries of fraud in peer review: A group of participants form...

November 22, 2021

Deep Learning for the Physical Sciences

Speaker: Max Welling (University of Amsterdam)

Event Recording:
A number of fields, most prominently speech, vision, and NLP have been disrupted by deep learning technology. A natural question is: "which application areas will follow next?".  My prediction is that the physical sciences will experience an...

November 29, 2021

Hierarchical Reinforcement Learning: Framework ad Recent Results

Speaker: Doina Precup (McGill University)

Reinforcement Learning allows intelligent agents to learn by interacting with their environment over time and receiving rewards. Hierarchical Reinforcement Learning (HRL) approaches promise to provide more efficient solutions to sequential...