DocumentCode
3353265
Title
A convergence analysis on a multilayered neural network
Author
Shin, Seiichi
Author_Institution
Dept. of Math. Eng. & Inf. Phys., Tokyo Univ., Japan
fYear
1994
fDate
5-9 Dec 1994
Firstpage
235
Lastpage
239
Abstract
In this paper, the learning gain of neural networks is reconsidered from the viewpoint of the adaptive control systems. We present here a novel learning law for a multilayered neural network, which is a class of σ-modified adaptive law used in robust adaptive control systems. We present a brief proof of boundedness of the estimator to be learned and a simple numerical simulation, where we show the viability of the proposed learning law
Keywords
adaptive control; convergence of numerical methods; feedforward neural nets; learning (artificial intelligence); neurocontrollers; robust control; adaptive control systems; boundedness; convergence analysis; estimator; learning gain; multilayered neural network; robust control; Adaptive control; Convergence; Equations; Multi-layer neural network; Neural networks; Numerical simulation; Physics; Programmable control; Robust control; Robustness;
fLanguage
English
Publisher
ieee
Conference_Titel
Industrial Technology, 1994., Proceedings of the IEEE International Conference on
Conference_Location
Guangzhou
Print_ISBN
0-7803-1978-8
Type
conf
DOI
10.1109/ICIT.1994.467122
Filename
467122
Link To Document