Location and stability of the equilibria of nonlinear neural networks
- 1 January 1991
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1955-1960 vol.3
- https://doi.org/10.1109/ijcnn.1991.170664
Abstract
The number, location and stability behavior of the equilibria of arbitrary nonlinear neural networks are analyzed without resorting to energy arguments based on assumptions of symmetric interactions or no self-interactions. The following results are proved. Let H=Keywords
This publication has 7 references indexed in Scilit:
- Improved neural networks for analog-to-digital conversionCircuits, Systems, and Signal Processing, 1992
- Location and stability of the equilibria of nonlinear neural networksPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1991
- Simple 'neural' optimization networks: An A/D converter, signal decision circuit, and a linear programming circuitIEEE Transactions on Circuits and Systems, 1986
- “Neural” computation of decisions in optimization problemsBiological Cybernetics, 1985
- Neurons with graded response have collective computational properties like those of two-state neurons.Proceedings of the National Academy of Sciences, 1984
- Neural networks and physical systems with emergent collective computational abilities.Proceedings of the National Academy of Sciences, 1982
- The measure of the critical values of differentiable mapsBulletin of the American Mathematical Society, 1942