DocumentCode
2884847
Title
Stabilization and structure optimization of asymmetric neural networks
Author
Zeng, Huanglin ; Yu, Juebang
Author_Institution
Sichuan Inst. of Light Ind. & Chem. Technol., China
fYear
1991
fDate
16-17 Jun 1991
Firstpage
268
Abstract
A new approach for stabilizing asymmetric neural networks is suggested in the present paper. A nonlinear control system is used as the model of the given neural network, then by decomposing the interconnection matrix and by using the deremainder control technique, some asymptotically stable outputs can be attained as the network is driven by prescribed inputs. A structure optimization scheme for the network is also suggested following the same technique
Keywords
matrix algebra; neural nets; optimisation; stability; asymmetric neural networks; asymptotically stable outputs; deremainder control technique; interconnection matrix; nonlinear control system model; structure optimization; Artificial neural networks; Chemical industry; Chemical technology; Electrical equipment industry; Hopfield neural networks; Matrix decomposition; Neural networks; Neurons; Nonlinear control systems; Symmetric matrices;
fLanguage
English
Publisher
ieee
Conference_Titel
Circuits and Systems, 1991. Conference Proceedings, China., 1991 International Conference on
Conference_Location
Shenzhen
Type
conf
DOI
10.1109/CICCAS.1991.184336
Filename
184336
Link To Document