Hopfield, J. J. (1987) Learning algorithms and probability distributions in feed-forward and feed-back networks. Proceedings of the National Academy of Sciences of the United States of America, 84 (23). pp. 8429-8433. ISSN 0027-8424 http://resolver.caltech.edu/CaltechAUTHORS:HOPpnas87
See Usage Policy.
Use this Persistent URL to link to this item: http://resolver.caltech.edu/CaltechAUTHORS:HOPpnas87
Learning algorithms have been used both on feed-forward deterministic networks and on feed-back statistical networks to capture input-output relations and do pattern classification. These learning algorithms are examined for a class of problems characterized by noisy or statistical data, in which the networks learn the relation between input data and probability distributions of answers. In simple but nontrivial networks the two learning rules are closely related. Under some circumstances the learning problem for the statistical networks can be solved without Monte Carlo procedures. The usual arbitrary learning goals of feed-forward networks can be given useful probabilistic meaning.
|Additional Information:||© 1987 by the National Academy of Sciences. Contributed by J. J. Hopfield, August 17, 1987. I acknowledge helpful conversations with D.W. Tank, E. Baum, and S. Solla. This work was supported by contract N00014-K-0377 from the Office of Naval Research. The publication costs of this article were defrayed in part by page charge payment. This article must therefore be hereby marked "advertisement" in accordance with 18 U.S.C. §1734 solely to indicate this fact.|
|Usage Policy:||No commercial reproduction, distribution, display or performance rights in this work are provided.|
|Deposited By:||Tony Diaz|
|Deposited On:||14 Aug 2007|
|Last Modified:||26 Dec 2012 09:39|
Repository Staff Only: item control page