Title :
Quadratic-type Lyapunov functions for competitive neural networks with different time-scales
Author :
Meyer-Bäse, Anke ; Ohl, Frank ; Scheich, Henning
Author_Institution :
Federal Inst. for Neurobiol., Magdeburg, Germany
Abstract :
The dynamics of complex neural networks must include the aspects of long and short-term memory. The behaviour of the network is characterized by an equation of neural activity as a fast phenomenon and by an equation of synaptic modification as a slow part of the neural system. We present a quadratic-type Lyapunov function for the flow of a competitive neural system with fast and slow dynamic variables
Keywords :
Hebbian learning; Lyapunov methods; asymptotic stability; circuit stability; neural nets; nonlinear systems; singularly perturbed systems; Hebbian learning; asymptotic stability; competitive neural networks; complex neural networks; dynamics; nonlinear singularly perturbed systems; quadratic-type Lyapunov functions; synaptic modification; time-scales; Asymptotic stability; Convergence; Differential equations; Fluid dynamics; Hebbian theory; Large-scale systems; Lyapunov method; Neural networks; Neurons; Spatiotemporal phenomena;
Conference_Titel :
Neural Networks, 1995. Proceedings., IEEE International Conference on
Conference_Location :
Perth, WA
Print_ISBN :
0-7803-2768-3
DOI :
10.1109/ICNN.1995.487299
