UNIW 2012 - The Uncertainty in Natural Intelligence Workshop

Website | Edit Freely

Category UNIW 2012

Deadline: July 01, 2012 | Date: August 18, 2012

Venue/Country: Catalina Island, U.S.A

Updated: 2012-05-01 23:22:23 (GMT+9)

Call For Papers - CFP

http://cocosci.berkeley.edu/uai2012/

Call for participation

Workshop date: August 18, 2012

Location: Catalina Island, CA, USA (near Los Angeles)

Submission deadline: July 1, 2012 at 11:59pm PST

Organizers:

Noah Goodman (Stanford University)

Thomas Griffiths (University of California, Berkeley)

Josh Tenenbaum (Massachusetts Institute of Technology)

Joseph Austerweil (University of California, Berkeley)

Invited speakers:

Mark Steyvers (University of California, Irvine)

Xiaojin (Jerry) Zhu (University of Wisconsin-Madison)

Steve Piantadosi (University of Rochester)

Keith Holyoak (University of California, Los Angeles)

Workshop format:

The full day workshop consists of talks from the invited speakers and organizers, poster

spotlights (very brief talks), a session of contributed posters, and a discussion between

the audience members, speakers, and organizers.

Submission instructions:

Please email 1 page abstracts to uaihumanlearning2012gmail.com by July 1, 2012 at

11:59pm PST. All abstracts will be reviewed by the organizing committee and notifications

will be sent out by July 15, 2012.

Important dates:

Deadline for poster submissions: July 1, 2012 at 11:59pm PST

Notification: July 15, 2012

Workshop date: August 18, 2012

Workshop description:

Some of the hardest problems in artificial intelligence, such as feature and concept

learning, are solved seemingly effortlessly by people. These are problems of inductive

inference, which are difficult because there are many solutions that are consistent with

the information explicitly given with the problem (e.g., solving ab=2 for the value of a

without being given any additional information).

People solve problems of inductive inference by favoring solutions that are consistent

with their prior knowledge and penalizing solutions that are inconsistent with prior

beliefs. Bayesian inference provides a formal calculus for how people should update their

prior belief in each solution in light of their observations. Prior beliefs are

formulated as a probability distribution over the unobserved solutions. This methodology

has provided a successful paradigm for exploring formal solutions to how people solve

inductive problems.

Using Bayesian inference to formally represent human solutions to inductive problems not

only provides a computational explanation of human behavior, but also offers novel

methods for solving difficult problems in artificial intelligence. In this workshop, we

present recent computational successes in human learning as a source of new artificial

intelligence algorithms by exploiting the common computational language of these two

communities, probability theory. This workshop is a forum for researchers in artificial

intelligence, machine learning, and human learning, all interested in the same inductive

problems, to discuss computational methodologies, insights, and research questions. We

hope to foster a dialogue that leads to a greater understanding of human learning and

further unites these two areas of research.