Stability theory of universal learning network

Author

Hirasawa, Kotaro ; Ohbayashi, Masanao ; Koga, Masaru ; Kusumi, Naohiro

Author_Institution

Dept. of Electr. & Electron. Syst. Eng., Kyushu Univ., Fukuoka, Japan

Volume

2

fYear

1996

fDate

14-17 Oct 1996

Firstpage

1352

Abstract

Higher order derivatives of the universal learning network (ULN) has been previously derived by forward and backward propagation computing methods, which can model and control the large scale complicated systems such as industrial plants, economic, social and life phenomena. In this paper, a new concept of nth order asymptotic orbital stability for the ULN is defined by using higher order derivatives of ULN and a sufficient condition of asymptotic orbital stability for ULN is derived. It is also shown that if 3rd order asymptotic orbital stability for a recurrent neural network is proved, higher order asymptotic orbital stability than 3rd order is guaranteed

Keywords

asymptotic stability; learning (artificial intelligence); recurrent neural nets; 3rd order asymptotic orbital stability; higher order derivatives; nth order asymptotic orbital stability; recurrent neural network; stability theory; sufficient condition; universal learning network; Asymptotic stability; Delay effects; Fluctuations; Industrial plants; Large-scale systems; Nonlinear control systems; Nonlinear systems; Sampling methods; Stability analysis; Sufficient conditions;

fLanguage

English

Publisher

ieee

Conference_Titel

Systems, Man, and Cybernetics, 1996., IEEE International Conference on

Conference_Location

Beijing

ISSN

1062-922X

Print_ISBN

0-7803-3280-6

Type

conf

DOI

10.1109/ICSMC.1996.571308

Filename

571308