The key challenge of intelligence is generalization: Cognitive Science Speaker Series Presentation
Speaker: Xaq Pitkow, Ph.D.
Title: The key challenge of intelligence is generalization
Short Bio: Xaq Pitkow is a computational neuroscientist who develops mathematical theories of the brain and general principles of intelligent systems. He focuses on how distributed nonlinear neural computation uses statistical reasoning to guide action in naturalistic tasks. Although he is a theorist, he did at one point perform neuroscience experiments, and still collaborates closely with experimentalists to help design experiments, analyze data, and ground theories. He was trained in physics as an undergrad at Princeton and went on to study biophysics for his Ph.D. at Harvard. He then took postdoctoral positions in the Center for Theoretical Neuroscience at Columbia and in the department of Brain and Cognitive Sciences at the University of Rochester. In 2013 he moved to Houston to become a faculty member at the Baylor College of Medicine in the Department of Neuroscience, with a joint appointment at Rice University in the Department of Electrical and Computer Engineering. After a decade there he moved to the Carnegie Mellon University, appointed in the Neuroscience Institute and with a courtesy appointment in the Department of Machine Learning. He is currently the Associate Director of the NSF AI Institute for Artificial and Natural Intelligence. On the side, he enjoys sculpting, digital art, musical improvisation, and world travel.
Abstract: The key challenge of intelligence is generalization. Xaq will present emerging theoretical principles of generalization that are shared between brains and machines, focusing on elements of computation at the small and large scale that may instantiate these principles.
ASL-English interpreters have been requested. Light refreshments will be provided.
Event Snapshot
When and Where
Who
Open to the Public
Interpreter Requested?
Yes