Adaptive sliding mode approach for learning in a feedforward neural network

被引：32

作者：

Yu, X ^{[1
]}

Zhihong, M

Rahman, SMM

机构：

[1] Univ Cent Queensland, Fac Informat & Commun, Rockhampton, Qld 4702, Australia

[2] Univ Tasmania, Dept Elect Engn & Comp Sci, Hobart, Tas, Australia

[3] Monash Univ, Dept Comp Sci & Software Engn, Clayton, Vic 3168, Australia

来源：

NEURAL COMPUTING & APPLICATIONS | 1998年 / 7卷 / 04期

关键词：

adaptive linear elements; back-propagation; sliding mode concept;

D O I：

10.1007/BF01428120

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

An adaptive learning algorithm is proposed for a feedforward neural network The design principle is based on the sliding mode concept. Unlike the existing algorithms, the adaptive learning algorithm developed does not require a priori knowledge of upper bounds of bounded signals. The convergence of the algorithm is established and conditions given. Simulations are presented to show the effectiveness of the algorithm.

引用

页码：289 / 294

页数：6

共 6 条

[1]

COLINAMORLES E, 1993, J SYSTEMS ENG, V1, P9

[2] Application of feedforward neural networks to dynamical system identification and control [J].

Kuschewski, John G. ;

Hui, Stefen ;

Zak, Stanislaw H. .

IEEE Transactions on Control Systems Technology, 1993, 1 (01) :37-49

[3] THE ADAPTATION OF PERCEPTRONS WITH APPLICATIONS TO INVERSE DYNAMICS IDENTIFICATION OF UNKNOWN DYNAMIC-SYSTEMS [J].

SIRARAMIREZ, HJ ;

ZAK, SH .

IEEE TRANSACTIONS ON SYSTEMS MAN AND CYBERNETICS, 1991, 21 (03) :634-643

[4]

[No title captured]

[5]

[No title captured]

[6]

[No title captured]

← 1 →