TY - GEN
T1 - Approach to learning in Hopfield neural networks
AU - Srinivasan, Sudhakar
AU - Moore, Kevin L.
AU - Naidu, D. Subbaram
PY - 1993/1/1
Y1 - 1993/1/1
N2 - 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.
AB - 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.
UR - http://www.scopus.com/inward/record.url?scp=0027335123&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=0027335123&partnerID=8YFLogxK
U2 - 10.23919/acc.1993.4793427
DO - 10.23919/acc.1993.4793427
M3 - Conference contribution
AN - SCOPUS:0027335123
SN - 0780308611
SN - 9780780308619
T3 - American Control Conference
SP - 2892
EP - 2893
BT - American Control Conference
PB - Publ by IEEE
T2 - Proceedings of the 1993 American Control Conference
Y2 - 2 June 1993 through 4 June 1993
ER -