Separable recursive training algorithms for feedforward neural networks

被引：7
|
作者：
Asirvadam, VS [1 ]
McLoone, SF [1 ]
Irwin, GW [1 ]
机构：
[1] Queens Univ Belfast, Sch Elect & Elect Engn, Intelligent Syst & Control Grp, Belfast BT9 5AH, Antrim, North Ireland
来源：
PROCEEDING OF THE 2002 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS, VOLS 1-3 | 2002年
关键词：
D O I：
10.1109/IJCNN.2002.1007667
中图分类号：
TP18 [人工智能理论];
学科分类号：
081104 ; 0812 ; 0835 ; 1405 ;
摘要：
Novel separable recursive training strategies are derived for the training of feedforward neural networks. These hybrid algorithms combine nonlinear recursive optimization of hidden layer nonlinear weights with recursive least square optimization of linear output layer weights in one integrated routine. Experimental results for two benchmark problems demonstrate the superiority of the new hybrid training schemes compared to conventional counterparts.
引用
收藏
页码：1212 / 1217
页数：2
相关论文
共 50 条
  • [1] New algorithms for training feedforward neural networks
    Kak, Subhash
    1600, Publ by Elsevier Science Publishers B.V., Amsterdam, Netherlands (15):
  • [2] NEW ALGORITHMS FOR TRAINING FEEDFORWARD NEURAL NETWORKS
    KAK, S
    PATTERN RECOGNITION LETTERS, 1994, 15 (03) : 295 - 298
  • [3] Training feedforward neural networks using neural networks and genetic algorithms
    Tellez, P
    Tang, Y
    INTERNATIONAL CONFERENCE ON COMPUTING, COMMUNICATIONS AND CONTROL TECHNOLOGIES, VOL 1, PROCEEDINGS, 2004, : 308 - 311
  • [4] Training feedforward neural networks using genetic algorithms
    1600, Morgan Kaufmann Publ Inc, San Mateo, CA, USA (01):
  • [5] Separable Recursive Training Algorithms with Switching Module
    Asirvadam, Vijanth S.
    NEURAL INFORMATION PROCESSING, PT 1, PROCEEDINGS, 2009, 5863 : 126 - 134
  • [6] EFFICIENT GENETIC ALGORITHMS FOR TRAINING LAYERED FEEDFORWARD NEURAL NETWORKS
    YOON, BJ
    HOLMES, DJ
    LANGHOLZ, G
    KANDEL, A
    INFORMATION SCIENCES, 1994, 76 (1-2) : 67 - 85
  • [7] Two regularizers for recursive least squared algorithms in feedforward multilayered neural networks
    Leung, CS
    Tsoi, AC
    Chan, LW
    IEEE TRANSACTIONS ON NEURAL NETWORKS, 2001, 12 (06): : 1314 - 1332
  • [8] ON TRAINING FEEDFORWARD NEURAL NETWORKS
    KAK, S
    PRAMANA-JOURNAL OF PHYSICS, 1993, 40 (01): : 35 - 42
  • [9] Training and structure design of feedforward neural networks by employing genetic algorithms
    Bohari, AR
    Mizuno, N
    1998 JAPAN-U.S.A. SYMPOSIUM ON FLEXIBLE AUTOMATION - PROCEEDINGS, VOLS I AND II, 1998, : 769 - 776
  • [10] An efficient recursive total least squares algorithm for training multilayer feedforward neural networks
    Choi, NJ
    Lim, JS
    Sung, KM
    ADVANCES IN NEURAL NETWORKS - ISNN 2005, PT 1, PROCEEDINGS, 2005, 3496 : 558 - 565
12345