Title :
Stability analysis techniques for competitive neural networks with different time-scales
Author :
Meyer-Bäse, Anke ; Ohl, Frank ; Scheich, Henning
Author_Institution :
Inst. for Digital Tech., Tech. Hochschule Darmstadt, Germany
Abstract :
We present new methods of analyzing the dynamics of a competitive neural system with different time scales: the K-monotone system theory developed by Kamke (1932) as a global analysis techniques, and the theory of singular perturbation as a local analysis method
Keywords :
Hebbian learning; asymptotic stability; circuit stability; dynamics; neural nets; nonlinear systems; singularly perturbed systems; Hebbian learning; K-monotone system; asymptotic stability; competitive neural networks; dynamics; large scale systems; nonlinear systems; singular perturbation; stability analysis; time-scales; Equations; Hebbian theory; Jacobian matrices; Lyapunov method; Network topology; Neural networks; Neurons; Spatiotemporal phenomena; Stability analysis; State-space methods;
Conference_Titel :
Neural Networks, 1995. Proceedings., IEEE International Conference on
Conference_Location :
Perth, WA
Print_ISBN :
0-7803-2768-3
DOI :
10.1109/ICNN.1995.487300