RECURSIVE SINGLE-LAYER NETS FOR OUTPUT ERROR DYNAMIC-MODELS

被引：2
作者：
BERGER, CS
机构：
[1] Department of Electrical and Computer Systems Engineering, Morash University, Clayton
来源：
IEEE TRANSACTIONS ON NEURAL NETWORKS | 1995年 / 6卷 / 02期
关键词：
D O I：
10.1109/72.363491
中图分类号：
TP18 [人工智能理论];
学科分类号：
081104 ; 0812 ; 0835 ; 1405 ;
摘要：
An algorithm for training recursive single-layer nets that has been shown to exhibit rapid convergence is presented. Convergence is not guaranteed, but a sufficient condition is given to justify the method. The method is demonstrated on a difficult modeling problem from bioengineering.
引用
收藏
页码：508 / 511
页数：4
相关论文
共 12 条
[1]  
Albus J. S., 1975, Transactions of the ASME. Series G, Journal of Dynamic Systems, Measurement and Control, V97, P220, DOI 10.1115/1.3426922
[2]  
BERGER CS, IN PRESS IEE P CONTR
[3]  
BERGER CS, 1993, IFAC PREPRINTS, V1, P333
[4]  
BERGER CS, 1983, IFAC S REAL TIME DIG, P98
[5]  
BROWN M, 1991, IEE CONF PUBL, P134
[6]  
Goodwin GC, 1984, ADAPTIVE FILTERING P
[7]   Theory and development of higher-order CMAC neural networks [J].
Lane, Stephen H. ;
Handelman, David A. ;
Gelfand, Jack J. .
IEEE Control Systems Magazine, 1992, 12 (02) :23-30
[8]   CMAC - AN ASSOCIATIVE NEURAL NETWORK ALTERNATIVE TO BACKPROPAGATION [J].
MILLER, WT ;
GLANZ, FH ;
KRAFT, LG .
PROCEEDINGS OF THE IEEE, 1990, 78 (10) :1561-1567
[9]   Fast Learning in Networks of Locally-Tuned Processing Units [J].
Moody, John ;
Darken, Christian J. .
NEURAL COMPUTATION, 1989, 1 (02) :281-294
[10]  
PARKS PC, 1989, AUTOMAT REM CONTR+, V50, P254
12