Title :
Global asymptotic stability of BAM neural networks with mixed delays
Author_Institution :
Found. Dept., Sichuan TOP Vocational Inst. of Inf. Technol., Chengdu, China
Abstract :
This paper presents a sufficient condition for the existence, uniqueness and global asymptotic stability of the equilibrium point for bidirectional associative memory (BAM) neural networks with mixed delays. The results impose constraint conditions on the network parameters of neural system independently of the delay parameter; and they are applicable to all bounded continuous non-monotonic neuron activation functions. The results derived in the literature.
Keywords :
asymptotic stability; content-addressable storage; neural nets; BAM neural network; bidirectional associative memory neural network; continuous non-monotonic neuron activation function; global asymptotic stability; mixed delays; Artificial neural networks; Associative memory; Asymptotic stability; Circuit stability; Delay; Equations; Stability analysis; BAM; mixed delays; neural networks; stability;
Conference_Titel :
Apperceiving Computing and Intelligence Analysis (ICACIA), 2010 International Conference on
Conference_Location :
Chengdu
Print_ISBN :
978-1-4244-8025-8
DOI :
10.1109/ICACIA.2010.5709868
