Global stability analysis of a general class of discontinuous neural networks with linear growth activation functions (Q730937)
From MaRDI portal
scientific article
| Language | Label | Description | Also known as |
|---|---|---|---|
| English | Global stability analysis of a general class of discontinuous neural networks with linear growth activation functions |
scientific article |
Statements
Global stability analysis of a general class of discontinuous neural networks with linear growth activation functions (English)
0 references
1 October 2009
0 references
A general class of neural networks is studied in the case when the neuron activation functions are modeled by discontinuous functions with linear growth. First the author proves the existence of periodic solutions for such nets by means of Leray-Schauder alternative theorem. Sufficient condition for global asymptotic stability of the periodic solutions is obtained using the matrix theory and generalized Lyapunov approach. Two illustrative examples are considered as well.
0 references
neural networks
0 references
global asymptotic stability
0 references
periodic solutions
0 references
Lyapunov approach
0 references
differential inclusions
0 references
