This article is cited in 1 paper

Short communications

The stability domain in the parameters space of recursive neural networks with hypercube topology

S. A. Ivanov

Chelyabinsk State Pedagogical University

Abstract: The stability conditions are described for the discrete neural networks. The stability domains in the parameters space are constructed. The problem is reduced to the stability problem of finite-difference matrix equations of higher order with delay. The main method to solve the problem is the stability cone.

Keywords: neural networks, finite-difference matrix equations, finite-difference equations stability, hypercube.

UDC: 517.96

Received: 07.05.2012