Convergence in discrete-time neural networks with specific performance
Author:
- 12 April 2001
- journal article
- research article
- Published by American Physical Society (APS) in Physical Review E
- Vol. 63 (5) , 051904
Abstract
We analyze convergence in discrete-time neural networks with specific performance such as decay rate and trajectory bounds in terms of componentwise absolute (exponential) stability. Simple necessary and sufficient stability and positive invariance conditions are presented, which allow us to design a convergent network with prescribed performance. Our approach is based on a decomposition of competitive-cooperative connectivity or inhibitory-excitatory interaction that abounds in neural networks, without assuming symmetry of the connection matrices. The key idea is that through the decomposition, we can always relate a competitive-cooperative network with a cooperative dynamical system. The latter possesses significant order-preserving properties that are basic to our analysis. The explicit division of connection weights into inhibitory and excitatory types offers a higher potential for relating formal neural network models to neurophysiology.Keywords
This publication has 17 references indexed in Scilit:
- Neural Networks and Fuzzy SystemsThe Journal of the Acoustical Society of America, 1998
- Componentwise stability of 1D and 2D linear discrete-time systemsAutomatica, 1997
- Exponential stability and trajectory bounds of neural networks under structural variationsIEEE Transactions on Circuits and Systems, 1991
- Analysis and synthesis techniques for Hopfield type synchronous discrete time neural networks with application to associative memoryIEEE Transactions on Circuits and Systems, 1990
- Dynamics of iterated-map neural networksPhysical Review A, 1989
- Qualitative analysis of neural networksIEEE Transactions on Circuits and Systems, 1989
- Emulating the dynamics for a class of laterally inhibited neural networksNeural Networks, 1989
- Cellular neural networks: applicationsIEEE Transactions on Circuits and Systems, 1988
- Cellular neural networks: theoryIEEE Transactions on Circuits and Systems, 1988
- Componentwise asymptotic stability of linear constant dynamical systemsIEEE Transactions on Automatic Control, 1984