The stability and design of nonlinear neural networks

The stability and design of nonlinear neural networks

0.00 Avg rating0 Votes
Article ID: iaor19982981
Country: United Kingdom
Volume: 35
Issue: 8
Start Page Number: 1
End Page Number: 8
Publication Date: Apr 1998
Journal: Computers & Mathematics with Applications
Authors: , ,
Keywords: programming: nonlinear
Abstract:

Based on the techniques of singular value decomposition and generalized inverse, two new methods for designing associative memories are presented. The two methods not only guarantee that each given vector is an equilibrium point of the network, but also guarantee the asymptotic stability of the equilibrium points. Examples show the effectiveness of the new methods.

Reviews

Required fields are marked *. Your email address will not be published.