Global stability and local stability of Hopfield neural networks with delays
- 1 November 1994
- journal article
- research article
- Published by American Physical Society (APS) in Physical Review E
- Vol. 50 (5), 4206-4213
- https://doi.org/10.1103/physreve.50.4206
Abstract
It is well known that Hopfield neural networks without delays exhibit no oscillations and possess global stability (i.e., all trajectories tend to some equilibrium). In the present paper we show that if the bound τβ∥∥0, interconnection matrix associated with delays, and gain of the neurons given by β, will exhibit similar qualitative properties as the original Hopfield neural network without delays (∥∥ denotes the matrix norm induced by the Euclidean vector norm). Specifically, we show that if the above bound is satisfied, then a Hopfield neural network without delays and a corresponding Hopfield neural network with delays will have identical asymptotically stable equilibria, and both networks are globally stable. In addition to the above, we provide in the present paper an effective method of determining the asymptotic stability of an equilibrium of a Hopfield neural network with delays, assuming that the above bound is satisfied. Our results are consistent with the results reported by Marcus and Westervelt [Phys. Rev. A 39, 347 (1989)]. Specifically, the present results, all of which are obtained by rigorous proof, give support to these results, which are based on linearization arguments, numerical simulations, and experimental results.
Keywords
This publication has 17 references indexed in Scilit:
- Qualitative analysis of neural networksIEEE Transactions on Circuits and Systems, 1989
- Cellular neural networks: applicationsIEEE Transactions on Circuits and Systems, 1988
- Qualitative analysis and synthesis of a class of neural networksIEEE Transactions on Circuits and Systems, 1988
- Collective computational properties of neural networks: New learning mechanismsPhysical Review A, 1986
- Computing with Neural Circuits: A ModelScience, 1986
- Information storage and retrieval in spin-glass like neural networksJournal de Physique Lettres, 1985
- Neurons with graded response have collective computational properties like those of two-state neurons.Proceedings of the National Academy of Sciences of the United States of America, 1984
- Absolute stability of global pattern formation and parallel memory storage by competitive neural networksIEEE Transactions on Systems, Man, and Cybernetics, 1983
- Neural networks and physical systems with emergent collective computational abilities.Proceedings of the National Academy of Sciences of the United States of America, 1982
- Periodic Solutions of Certain Nonlinear Integral Equations with a Time LagSIAM Journal on Applied Mathematics, 1976