NIPS Workshop: Overcomplete Representations and Nonlinear ICA

NIPS*99 Workshop

Overcomplete Representations and Nonlinear ICA

Organizers: Te-Won Lee, Kenneth Kreutz-Delgato and Michael S. Lewicki

When: Saturday, December 4, 1999, 7:30AM to 11:00AM and 4:30PM to 7:00PM

Where: Breckenridge, Colorado


Recently, there has been a great interest in statistical models for learning overcomplete representations. A popular method for learning data representations is Independent Component Analysis (ICA). Although most ICA research was focused on complete representations, we believe that statistical models with overcomplete representations will lead to new powerful techniques for signal- and image processing. There is also a link between overcomplete representations and efficient sensory coding in the brain which shows the vitality of the emerging new perspectives. An example is Hubel and Wiesel's finding of oriented receptive fields in cat visual cortex which has been substantiated by coding natural scenes (Olshausen, Bell, and Lewicki) using complete/overcomplete representations. The methods derived by considering statistical and information theoretic principles such can be used for coding images and audio signals which are more efficient than other traditional engineering methods.

The goal of this workshop is to bring together researchers who are interested in exchanging their ideas and exploring new theories for overcomplete representations. We anticipate talks on advanced topics in overcomplete representations, mixture models, nonlinear independent component analysis, information theoretic coding, image understanding, speech modeling, and pattern recognition using overcomplete representations.

The one-day workshop will have 12 speakers giving 20 min talks with 5 min discussion. The last 20 min will be reserved to discuss the talks and compile directions for future research.

List of Confirmed Speakers:

Eero P. Simoncelli (NY Univ)
Bruno Olshausen (UC Davis)
Tony Bell (Interval)
Mike Lewicki (CMU)
Jean-Pierre Nadal (Ecole Normale)
Shunichi Amari (RIKEN)
Joon-Hoon Oh (Postech)
Mark Girolami (Univ. of Paisley)
Ken Kreutz-Delgato & Baskhar Rao (UCSD)
Aapo Hyvaerinen, Erkki Oja (HUT)
Hagai Attias (UCL)
Sam Roweis (UCL)
Michael Zibulevsky & Barak Pearlmutter (UNM)
Naoki Saito (UC Davis)
Te-Won Lee (Salk & UCSD)
Allan Barros & Andrzej Cichocki (RIKEN)
Daniel Lee (Bell Labs) Gert Cauwenberghs (Johns Hopkins)


For further information, contact:
Te-Won Lee
Institute for Neural Computation, UCSD &
The Salk Institute, CNL
10010 N. Torrey Pines Road
La Jolla, CA 92037

Phone: 619-453-4100 x1527
Fax: 619-587-0417
WWW: http://www.cnl.salk.edu/~tewon/
e-mail: tewon@salk.edu


Te-Won Lee
Last modified: Tue Nov 16 16:07:59 PST 1999