Share Email Print
cover

Proceedings Paper

Inference and segmentation in cortical processing
Author(s): Yuan Liu; Guillermo A. Cecchi; A. Ravishankar Rao; James Kozloski; Charles C. Peck
Format Member Price Non-Member Price
PDF $14.40 $18.00
cover GOOD NEWS! Your organization subscribes to the SPIE Digital Library. You may be able to download this paper for free. Check Access

Paper Abstract

We present a modelling framework for cortical processing aimed at understanding how, maintaining biological plausibility, neural network models can: (a) approximate general inference algorithms like belief propagation, combining bottom-up and top-down information, (b) solve Rosenblatt's classical superposition problem, which we link to the binding problem, and (c) do so based on an unsupervised learning approach. The framework leads to two related models: the first model shows that the use of top-down feedback significantly improves the network's ability to perform inference of corrupted inputs; the second model, including oscillatory behavior in the processing units, shows that the superposition problem can be efficiently solved based on the unit's phases.

Paper Details

Date Published: 9 February 2006
PDF: 10 pages
Proc. SPIE 6057, Human Vision and Electronic Imaging XI, 60570Y (9 February 2006); doi: 10.1117/12.650804
Show Author Affiliations
Yuan Liu, IBM Thomas J. Watson Research Ctr. (United States)
Princeton Univ. (United States)
Guillermo A. Cecchi, IBM Thomas J. Watson Research Ctr. (United States)
A. Ravishankar Rao, IBM Thomas J. Watson Research Ctr. (United States)
James Kozloski, IBM Thomas J. Watson Research Ctr. (United States)
Charles C. Peck, IBM Thomas J. Watson Research Ctr. (United States)


Published in SPIE Proceedings Vol. 6057:
Human Vision and Electronic Imaging XI
Bernice E. Rogowitz; Thrasyvoulos N. Pappas; Scott J. Daly, Editor(s)

© SPIE. Terms of Use
Back to Top