Accession Number : ADA239606


Title :   Connectionist Models: Proceedings of the Summer School Held in San Diego, California on 1990


Corporate Author : CALIFORNIA UNIV SAN DIEGO LA JOLLA


Personal Author(s) : Touretzky, David S ; Elman, Jeffrey L ; SeJnowski, Terrence J ; Hinton, Geoffrey E


Full Text : http://www.dtic.mil/dtic/tr/fulltext/u2/a239606.pdf


Report Date : Jan 1990


Pagination or Media Count : 397


Abstract : The simplicity and locality of the contrastive Hebb synapse (CHS) used in Boltzmann machine learning makes it an attractive model for real biological synapses. The slow learning exhibited by the stochastic Boltzmann machine can be greatly improved by using a mean field approximation and it has been shown (Hinton, 1989) that the CHS also performs steepest descent in these deterministic mean field networks. A major weakness of the learning procedure, from a biological perspective, is that the derivation assumes detailed symmetry of the connectivity. Using networks with purely asymmetric connectivity, we show that the CHS still works in practice provided the connectivity is grossly symmetrical so that if unit i sends a connection to unit j, there are numerous indirect feedback paths from j to i.


Descriptors :   *LEARNING MACHINES , BIOLOGY , NETWORKS , PATHS , FEEDBACK , STEEPEST DESCENT METHOD , SYNAPSE , LEARNING , DETERMINANTS(MATHEMATICS) , BOLTZMANN EQUATION , SUMMER , SCHOOLS , MEAN


Subject Categories : Psychology


Distribution Statement : APPROVED FOR PUBLIC RELEASE