Title :
On the sufficient conditions for the stability of nonlinear continuous neural networks
Author_Institution :
Dept. of Electr. Eng., Southwest Jiaotong Univ., Sichuan, China
Abstract :
Based on the Maxwell minimum heating theorem and the stability criteria of continuous autonomous dynamic networks, the sufficient conditions for a stable content-addressable memory (CAM) neural network model are established. An example is given to illustrate the effect of the circuit parameters on the stability on the CAM neural network simulated by electronic devices. The approach presented should be helpful in stability analyses of other nonlinear continuous neural networks
Keywords :
content-addressable storage; neural nets; nonlinear network analysis; stability criteria; Maxwell minimum heating theorem; continuous autonomous dynamic networks; nonlinear continuous neural networks; stability criteria; stable content-addressable memory neural network model; CADCAM; Capacitors; Circuit stability; Computer aided manufacturing; Heating; Hopfield neural networks; Neural networks; Neurons; Stability analysis; Sufficient conditions;
Conference_Titel :
Industrial Electronics Society, 1990. IECON '90., 16th Annual Conference of IEEE
Conference_Location :
Pacific Grove, CA
Print_ISBN :
0-87942-600-4
DOI :
10.1109/IECON.1990.149316
