Title :
On oscillations in a class of nearly symmetric neural networks
Author :
Marco, M. Di ; Forti, M. ; Tesi, A.
Author_Institution :
Dipt. di Ingegneria dell´´Informazione, Siena Univ., Italy
Abstract :
This paper provides a structural condition on the nominal symmetric interconnection matrix of a neural network, which implies the existence of stable limit cycles generated via Hopf bifurcations, even for arbitrarily small perturbations of the interconnections
Keywords :
bifurcation; circuit stability; eigenvalues and eigenfunctions; limit cycles; matrix algebra; neural nets; Hopf bifurcations; eigenvalues; limit cycles; neural networks; oscillations; perturbations; stability; structural condition; symmetric interconnection matrix; Bifurcation; Differential equations; Eigenvalues and eigenfunctions; Intelligent networks; Limit-cycles; Neural networks; Neurons; Robust stability; Stationary state; Symmetric matrices;
Conference_Titel :
Decision and Control, 2001. Proceedings of the 40th IEEE Conference on
Conference_Location :
Orlando, FL
Print_ISBN :
0-7803-7061-9
DOI :
10.1109/.2001.980686
