[Nrg-l] FW: 9.520: Learning Theory and Applications, Spring 2006; starts Wednesday, February 8th

Mark Crovella crovella at cs.bu.edu
Wed Jan 17 08:09:38 EST 2007


-----Original Message-----
From: seminars-bounces at lists.csail.mit.edu
[mailto:seminars-bounces at lists.csail.mit.edu] On Behalf Of Tomaso Poggio
Sent: Wednesday, January 17, 2007 7:43 AM
To: csail-all.lists at MIT.EDU; bcs-talks at MIT.EDU; pclm-all at MIT.EDU;
mcgovern at MIT.EDU; ling-fac at MIT.EDU; ling-grad at MIT.EDU;
mcgoverninstitute at MIT.EDU; seminars at csail.mit.edu; msgs at media.mit.edu;
conquest at hms.harvard.edu; lazar at nmr.mgh.harvard.edu
Subject: 9.520: Learning Theory and Applications, Spring 2006; starts
Wednesday, February 8th

Class Times:Monday and Wednesday 10:30-12:00; starts Wednesday, February
Location: 46-5056
Instructors:Tomaso Poggio, Alex Rakhlin, Ryan Rifkin, Andrea Caponnetto
Office Hours:By appointment Email Contact :9.520 at mit.edu





The 2007 spring edition is an updated version of the course which has
been running for several years. It focuses on the problem of supervised
and unsupervised learning from the perspective of modern statistical
learning theory, starting with the theory of multivariate function
approximation from sparse data. Develops basic tools such as
regularization, including support vector machines for regression and
classification. Derives generalization bounds using stability. Discusses
current research topics such as manifold regularization, feature
selection, bayesian connections and techniques, and online learning. It
emphasizes more than in previous years applications in several areas:
computer vision, speech recognition and bioinformatics. It discusses
advances in the neuroscience of cortex and their impact on learning
theory and applications. Final projects and hands-on applications and

Tomaso Poggio
Eugene McDermott Professor

McGovern Institute
CSAIL (Computer Science and Artificial Intelligence Lab) Brain Sciences
Department M.I.T., 46-5177B,
43 Vassar Street
Cambridge, MA 02142
E-mail: tp at ai.mit.edu

My antiSpam keyword is E25-218. If you insert "E25-218", possibly at the
top of the *body* of your msg, my antispam filters will let your msg go
through. With spam getting worse every day, you may need to use the
keyword to be sure that your msg does not end in the trash can!

Web: http://cbcl.mit.edu/people/poggio/tpcv-current.htm
CBCL-Web-page: http://cbcl.mit.edu/
Phone: 617-253-5230
Fax: 617-253-2964

Seminars mailing list
Seminars at lists.csail.mit.edu

More information about the Nrg-l mailing list