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
    Lane, Stephen H.
    Handelman, David A.
    Gelfand, Jack J.
    [J]. IEEE Control Systems Magazine, 1992, 12 (02): : 23 - 30
  • [8] CMAC - AN ASSOCIATIVE NEURAL NETWORK ALTERNATIVE TO BACKPROPAGATION
    MILLER, WT
    GLANZ, FH
    KRAFT, LG
    [J]. PROCEEDINGS OF THE IEEE, 1990, 78 (10) : 1561 - 1567
  • [9] Fast Learning in Networks of Locally-Tuned Processing Units
    Moody, John
    Darken, Christian J.
    [J]. NEURAL COMPUTATION, 1989, 1 (02) : 281 - 294
  • [10] PARKS PC, 1989, AUTOMAT REM CONTR+, V50, P254
12