Title :
Analysis of global exponential stability for a class of bidirectional associative memory networks
Author :
Wan, Hongxia ; He, Chen ; Yu, Juebang
Author_Institution :
Dept. of Electron. Eng., Shanghai Jiao Tong Univ., China
Abstract :
In real-time applications of bi-directional associative memory (BAM) networks, a global exponential stable equilibrium is highly desired. The existence, uniqueness and global exponential stability for a class of BAM networks are studied in the present paper, the signal function of neurons is assumed to be piece-wise linear from the engineering point of view. A very concise condition for an equilibrium of such network being global exponential stable is derived, which makes the practical design of this kind of network an easy job.
Keywords :
asymptotic stability; content-addressable storage; piecewise linear techniques; BAM; bidirectional associative memory networks; global exponential stability; piece-wise linear; signal function; uniqueness; Associative memory; Bidirectional control; Bismuth; Circuits; Erbium; Magnesium compounds; Neural networks; Neurons; Piecewise linear techniques; Stability analysis;
Conference_Titel :
Circuits and Systems, 2003. ISCAS '03. Proceedings of the 2003 International Symposium on
Print_ISBN :
0-7803-7761-3
DOI :
10.1109/ISCAS.2003.1206402
