GEOMETRICAL LEARNING ALGORITHM FOR MULTILAYER NEURAL NETWORKS IN A BINARY FIELD

被引:8
|
作者
PARK, SK
KIM, JH
机构
[1] TENNESSEE TECHNOL UNIV,DEPT ELECT ENGN,COOKEVILLE,TN 38505
[2] UNIV SW LOUISIANA,CTR ADV COMP STUDIES,LAFAYETTE,LA 70504
关键词
BINARY FIELD; CONVERGENCE; HARDLIMITING NEURONS; INTEGER WEIGHTS; LEARNING; NEURAL NETWORKS;
D O I
10.1109/12.238491
中图分类号
TP3 [计算技术、计算机技术];
学科分类号
0812 ;
摘要
This correspondence introduces a geometrical expansion learning algorithm for multilayer neural networks using unipolar binary neurons with integer connection weights, which guarantees convergence for any Boolean function. Neurons in the hidden layer develop as necessary without supervision. In addition, the computational amount is much less than that of the backpropagation algorithm.
引用
下载
收藏
页码:988 / 992
页数:5
相关论文
共 50 条
  • [21] Least square based constructive learning algorithm for multilayer neural networks
    Li, Jianghong
    Hu, Zhaowen
    Changsha Dianli Xueyuan Xuebao/Journal of Changsha University of Electric Power, 1999, 14 (02): : 127 - 131
  • [22] Geometrical methods in neural networks and learning
    Fiori, S
    Amari, S
    NEUROCOMPUTING, 2005, 67 (1-4 SUPPL.) : 1 - 7
  • [23] A mean field learning algorithm for unsupervised neural networks
    Saul, L
    Jordan, M
    LEARNING IN GRAPHICAL MODELS, 1998, 89 : 541 - 554
  • [24] Learning with regularizers in multilayer neural networks
    Saad, D
    Rattray, M
    PHYSICAL REVIEW E, 1998, 57 (02) : 2170 - 2176
  • [25] Optimal learning in multilayer neural networks
    Winther, O.
    Lautrup, B.
    Zhang, J.-B.
    Physical Review E. Statistical Physics, Plasmas, Fluids, and Related Interdisciplinary Topics, 1997, 55 (1-B pt B):
  • [26] Optimal learning in multilayer neural networks
    Winther, O
    Lautrup, B
    Zhang, JB
    PHYSICAL REVIEW E, 1997, 55 (01) : 836 - 844
  • [27] LEARNING ALGORITHMS FOR MULTILAYER NEURAL NETWORKS
    AVEDYAN, ED
    AUTOMATION AND REMOTE CONTROL, 1995, 56 (04) : 541 - 551
  • [28] A Constructive Learning Algorithm Based on Division of Training Data for Multilayer Neural Networks
    Uno, T.
    Koakutsu, S.
    Hirata, H.
    Denki Gakkai Ronbunshi. C, Erekutoronikusu Joho Kogaku, Shisutemu, 116 (10):
  • [29] Sliding mode algorithm for online learning in analog multilayer feedforward neural networks
    Shakev, NG
    Topalov, AV
    Kaynak, O
    ARTIFICAIL NEURAL NETWORKS AND NEURAL INFORMATION PROCESSING - ICAN/ICONIP 2003, 2003, 2714 : 1064 - 1072
  • [30] An efficient learning algorithm with second-order convergence for multilayer neural networks
    Ninomiya, H
    Tomita, C
    Asai, H
    PROCEEDINGS OF THE INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS 2003, VOLS 1-4, 2003, : 2028 - 2032