Title :
Flow invariance for competitive neural networks with different time-scales
Author :
Meyer-Baese, Anke
Author_Institution :
Dept. of Electr. & Comput. Eng., Florida State Univ., Tallahassee, FL
fDate :
6/24/1905 12:00:00 AM
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 an equation of synaptic modification as a slow part of the neural system. We present a method of analyzing the dynamics of a system with different time scales based on the theory of flow invariance. We are able to show the conditions under which the solutions of such a system are bounded being less restrictive than with the K-monotone theory
Keywords :
dynamics; invariance; neural nets; unsupervised learning; competitive neural networks; complex neural networks; dynamics; fast phenomenon; flow invariance; long short-term memory; neural activity; short-term memory; synaptic modification; time-scales; Convergence; Differential equations; Hebbian theory; Interference; Large-scale systems; Neural networks; Neurons; Nonlinear dynamical systems; Stability criteria; State-space methods;
Conference_Titel :
Neural Networks, 2002. IJCNN '02. Proceedings of the 2002 International Joint Conference on
Conference_Location :
Honolulu, HI
Print_ISBN :
0-7803-7278-6
DOI :
10.1109/IJCNN.2002.1005586
