HOME HELP FEEDBACK SUBSCRIPTIONS ARCHIVE SEARCH TABLE OF CONTENTS		QUICK SEARCH:   [advanced] Author: Keyword(s): Year:  Vol:  Page:

This Article Full Text Full Text (PDF) Alert me when this article is cited Alert me if a correction is posted Services Similar articles in this journal Similar articles in PubMed Alert me to new issues of the journal Download to citation manager Citing Articles Citing Articles via HighWire Citing Articles via Google Scholar Google Scholar Articles by Saul, L. K. Articles by Jordan, M. I. Search for Related Content PubMed PubMed Citation Articles by Saul, L. K. Articles by Jordan, M. I.

Attractor Dynamics in Feedforward Neural Networks

AT&T Labs—Research, Florham Park, NJ 07932, U.S.A.

Michael I. Jordan

University of California, Berkeley, CA 94720, U.S.A.

We study the probabilistic generative models parameterized by feedforward neural networks. An attractor dynamics for probabilistic inference in these models is derived from a mean field approximation for large, layered sigmoidal networks. Fixed points of the dynamics correspond to solutions of the mean field equations, which relate the statistics of each unit to those of its Markov blanket. We establish global convergence of the dynamics by providing a Lyapunov function and show that the dynamics generate the signals required for unsupervised learning. Our results for feedforward networks provide a counterpart to those of Cohen-Grossberg and Hopfield for symmetric networks.

This article has been cited by other articles:

				G. E. Hinton Training Products of Experts by Minimizing Contrastive Divergence Neural Comput., August 1, 2002; 14(8): 1771 - 1800. [Abstract] [Full Text] [PDF]