Approach to learning in Hopfield neural networks

Sudhakar Srinivasan, Kevin L. Moore, D. Subbaram Naidu

Research output: Chapter in Book/Report/Conference proceedingConference contribution


In this paper we present some preliminary ideas for the design of a continuous nonlinear neural networks with `learning.' Specifically, we introduce the idea of learning in Hopfield recursive neural networks. The network is trained so that application of a set of inputs produces the desired set of outputs. A method is developed to determine the interconnecting weights for the network, so as to achieve the desired stable equilibrium points. Also, this method illustrates a way to `learn' the interconnecting weights that are not computed a priori. Conditions are obtained for the asymptotic stability of the equilibrium points. An illustrative simulation is presented.

Original languageEnglish (US)
Title of host publicationAmerican Control Conference
PublisherPubl by IEEE
Number of pages2
ISBN (Print)0780308611, 9780780308619
StatePublished - Jan 1 1993
EventProceedings of the 1993 American Control Conference - San Francisco, CA, USA
Duration: Jun 2 1993Jun 4 1993

Publication series

NameAmerican Control Conference


OtherProceedings of the 1993 American Control Conference
CitySan Francisco, CA, USA


Dive into the research topics of 'Approach to learning in Hopfield neural networks'. Together they form a unique fingerprint.

Cite this