Monthly
288 pp. per issue
6 x 9, illustrated
ISSN
0899-7667
E-ISSN
1530-888X
2014 Impact factor:
2.21

Neural Computation

January 2009, Vol. 21, No. 1, Pages 101-120
(doi: 10.1162/neco.2009.11-07-637)
© 2008 Massachusetts Institute of Technology
A New Approach for Estimating the Attraction Domain for Hopfield-Type Neural Networks
Article PDF (192.74 KB)
Abstract

In this letter, using methods proposed by E. Kaslik, St. Balint, and their colleagues, we develop a new method, expansion approach, for estimating the attraction domain of asymptotically stable equilibrium points of Hopfield-type neural networks. We prove theoretically and demonstrate numerically that the proposed approach is feasible and efficient. The numerical results that obtained in the application examples, including the network system considered by E. Kaslik, L. Brăescu, and St. Balint, indicate that the proposed approach is able to achieve better attraction domain estimation.