On the design of dynamic associative neural memories
Date
1994
Authors
Savran, M. E.
Morgül, Ö.
Advisor
Instructor
Source Title
IEEE Transactions on Neural Networks
Print ISSN
1045-9227
Electronic ISSN
Publisher
IEEE
Volume
5
Issue
3
Pages
489 - 492
Language
English
Type
Article
Journal Title
Journal ISSN
Volume Title
Abstract
We consider the design problem for a class of discrete-time and continuous-time neural networks. We obtain a characterization of all connection weights that store a given set of vectors into the network; that is, each given vector becomes an equilibrium point of the network. We also give sufficient conditions that guarantee the asymptotic stability of these equilibrium points.
Course
Other identifiers
Book Title
Keywords
Convergence of numerical methods, Mathematical models, Neural networks, System stability, Systems analysis, Vectors, Asymptotic stability, Continuous time neural networks, Discrete time neural networks, Dynamic associative neural memories, Equilibrium points, Associative storage