Matrix-update for accelerated on-line learning in multilayer neural networks

被引：2
|
作者：
Bos, S [1 ]
机构：
[1] RIKEN, Lab Informat Synth, Brain Sci Inst, Wako, Saitama 35101, Japan
来源：
JOURNAL OF PHYSICS A-MATHEMATICAL AND GENERAL | 1998年 / 31卷 / 22期
关键词：
D O I：
10.1088/0305-4470/31/22/002
中图分类号：
O4 [物理学];
学科分类号：
0702 ;
摘要：
In this letter we re-examine the emergence of plateaus or symmetric phases in online learning of a committee machine. We propose a simple matrix-update in order to avoid the symmetric phase. Simulations show that the length of the plateaus can be considerably decreased. Annealing of the learning rate can then be applied much earlier, making on-line learning more effective.
引用
收藏
页码：L413 / L417
页数：5
相关论文
共 50 条
  • [41] On-Line Extreme Learning Machine for Training Time-Varying Neural Networks
    Ye, Yibin
    Squartini, Stefano
    Piazza, Francesco
    BIO-INSPIRED COMPUTING AND APPLICATIONS, 2012, 6840 : 49 - 54
  • [42] Robust neural networks with on-line learning for blind identification and blind separation of sources
    Cichocki, A
    Unbehauen, R
    IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS I-REGULAR PAPERS, 1996, 43 (11) : 894 - 906
  • [43] On-line Gauss-Newton-based learning for fully recurrent neural networks
    Vartak, A. A.
    Georgiopoulos, M.
    Anagnostopoulos, G. C.
    NONLINEAR ANALYSIS-THEORY METHODS & APPLICATIONS, 2005, 63 (5-7) : E867 - E876
  • [44] Globally optimal on-line learning rules for multi-layer neural networks
    Rattray, M
    Saad, D
    JOURNAL OF PHYSICS A-MATHEMATICAL AND GENERAL, 1997, 30 (22): : L771 - L776
  • [45] On-line supervised learning for dynamic security classification using probabilistic neural networks
    Gavoyiannis, AE
    Voumvoulakis, EM
    Hatziargyriou, ND
    2005 IEEE POWER ENGINEERING SOCIETY GENERAL MEETING, VOLS, 1-3, 2005, : 2669 - 2675
  • [46] Theoretical analysis of batch and on-line training for gradient descent learning in neural networks
    Nakama, Takehiko
    NEUROCOMPUTING, 2009, 73 (1-3) : 151 - 159
  • [47] Sensor validation using hardware-based on-line learning neural networks
    Napolitano, MR
    Silvestri, G
    Windon, DA
    Casanova, JL
    Innocenti, M
    IEEE TRANSACTIONS ON AEROSPACE AND ELECTRONIC SYSTEMS, 1998, 34 (02) : 456 - 468
  • [48] On-line learning networks: Framework and scenarios
    Bottino, Rosa Maria
    EDUCATION AND INFORMATION TECHNOLOGIES, 2007, 12 (02) : 93 - 105
  • [49] On-line learning networks: Framework and scenarios
    Rosa Maria Bottino
    Education and Information Technologies, 2007, 12 (2) : 93 - 105
  • [50] On-line adaptation of neural networks for bioprocess control
    Gadkar, KG
    Mehra, S
    Gomes, J
    COMPUTERS & CHEMICAL ENGINEERING, 2005, 29 (05) : 1047 - 1057
12345