Seminar on Computational Learning and Adaptation

Goals of the Seminar

For well over a decade, research on computational approaches to learning and adaptation has been viewed as a central topic in many disciplines, including artificial intelligence, molecular biology, cognitive psychology, complexity theory, decision theory, pattern recognition, and statistics. Unfortunately, researchers in these paradigms do not communicate with each other as often as they might, leading to duplicated effort and missed insights that can come from interdisciplinary exchange.

The Seminar on Computational Learning and Adaptation is designed to improve communication among the local researchers who have interests in computational approaches to learning and adaption, broadly defined. Talks cover a variety of representations for learned knowledge - logical expressions, neural networks, stored cases, and probabilistic summaries, to name a few - and report different approaches to evaluation - applied, experimental, theoretical, and psychological. Open discussion aims to establish a common language and increase the chances of future collaborations.

Although the Seminar always takes place at Stanford University, it typically starts at 4:15 PM, when parking is free for participants from off campus. In fact, many regular attendees come from nearby corporate and government research centers, as do a large fraction of the Seminar's speakers. If you would like to be added to the seminar mailing list, or if you are interested in giving a talk in the series, send email to langley@csli.stanford.edu or dwilkins@stanford.edu.