Nonlinear Dynamics and Symbolic Dynamics of Neural Networks
- 1 September 1992
- journal article
- Published by MIT Press in Neural Computation
- Vol. 4 (5) , 621-642
- https://doi.org/10.1162/neco.1992.4.5.621
Abstract
A piecewise linear equation is proposed as a method of analysis of mathematical models of neural networks. A symbolic representation of the dynamics in this equation is given as a directed graph on an N-dimensional hypercube. This provides a formal link with discrete neural networks such as the original Hopfield models. Analytic criteria are given to establish steady states and limit cycle oscillations independent of network dimension. Model networks that display multiple stable limit cycles and chaotic dynamics are discussed. The results show that such equations are a useful and efficient method of investigating the behavior of neural networks.Keywords
This publication has 19 references indexed in Scilit:
- Modulation of Neural Networks for BehaviorAnnual Review of Neuroscience, 1991
- Sustained oscillations in a symmetric cooperative-competitive neural network: Disproof of a conjecture about content addressable memoryNeural Networks, 1988
- Neural NetsQuarterly Reviews of Biophysics, 1988
- Neurons with graded response have collective computational properties like those of two-state neurons.Proceedings of the National Academy of Sciences, 1984
- Chaos in neurobiologyIEEE Transactions on Systems, Man, and Cybernetics, 1983
- Order and chaos in neural systems: An approach to the dynamics of higher brain functionsIEEE Transactions on Systems, Man, and Cybernetics, 1983
- Structure and dynamics of neural network oscillatorsBrain Research, 1979
- Stable oscillations in mathematical models of biological control systemsJournal of Mathematical Biology, 1978
- NEURAL CIRCUITS FOR GENERATING RHYTHMIC MOVEMENTSAnnual Review of Biophysics and Bioengineering, 1978
- Combinatorial and topological methods in nonlinear chemical kineticsThe Journal of Chemical Physics, 1975