Adaptive training and pruning in feedforward networks

被引:0
|
作者
Chang, SJ [1 ]
Sum, J
Wong, KW
Leung, CS
机构
[1] Nankai Univ, Inst Modern Opt, Tianjin 300071, Peoples R China
[2] City Univ Hong Kong, Dept Elect Engn, Hong Kong, Hong Kong, Peoples R China
关键词
D O I
10.1049/el:20010074
中图分类号
TM [电工技术]; TN [电子技术、通信技术];
学科分类号
0808 ; 0809 ;
摘要
A local extended Kalman filter training and pruning approach is proposed to train feedforvard networks with the goal of reducing the computational complexity and storage requirement in large-scale practical problems. The performance of the proposed algorithm is demonstrated for the problem of handwritten digit recognition.
引用
收藏
页码:106 / 107
页数:2
相关论文
共 50 条
  • [41] Neighborhood based modified backpropagation algorithm using adaptive learning parameters for training feedforward neural networks
    Kathirvalavakumar, T.
    Subavathi, S. Jeyaseeli
    NEUROCOMPUTING, 2009, 72 (16-18) : 3915 - 3921
  • [42] On adaptive learning rate that guarantees convergence in feedforward networks
    Behera, Laxmidhar
    Kumar, Swagat
    Patnaik, Awhan
    IEEE TRANSACTIONS ON NEURAL NETWORKS, 2006, 17 (05): : 1116 - 1125
  • [43] Adaptive regression estimation with multilayer feedforward neural networks
    Kohler, M
    Krzyzak, A
    2004 IEEE INTERNATIONAL SYMPOSIUM ON INFORMATION THEORY, PROCEEDINGS, 2004, : 467 - 467
  • [44] Adaptive regression estimation with multilayer feedforward neural networks
    Kohler, M
    Krzyzak, A
    JOURNAL OF NONPARAMETRIC STATISTICS, 2005, 17 (08) : 891 - 913
  • [45] A NOVEL FAST FEEDFORWARD NEURAL NETWORKS TRAINING ALGORITHM
    Bilski, Jaroslaw
    Kowalczyk, Bartosz
    Marjanski, Andrzej
    Gandor, Michal
    Zurada, Jacek
    JOURNAL OF ARTIFICIAL INTELLIGENCE AND SOFT COMPUTING RESEARCH, 2021, 11 (04) : 287 - 306
  • [46] Training feedforward neural networks using genetic algorithms
    1600, Morgan Kaufmann Publ Inc, San Mateo, CA, USA (01):
  • [47] A FAST NEW ALGORITHM FOR TRAINING FEEDFORWARD NEURAL NETWORKS
    SCALERO, RS
    TEPEDELENLIOGLU, N
    IEEE TRANSACTIONS ON SIGNAL PROCESSING, 1992, 40 (01) : 202 - 210
  • [48] Successive approximation training algorithm for feedforward neural networks
    Liang, YC
    Feng, DP
    Lee, HP
    Lim, SP
    Lee, KH
    NEUROCOMPUTING, 2002, 42 : 311 - 322
  • [49] A constructive algorithm for feedforward neural networks with incremental training
    Liu, DR
    Chang, TS
    Zhang, Y
    IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS I-REGULAR PAPERS, 2002, 49 (12) : 1876 - 1879
  • [50] Evolutional design and training algorithm for feedforward neural networks
    Takahashi, H
    Nakajima, M
    IEICE TRANSACTIONS ON INFORMATION AND SYSTEMS, 1999, E82D (10) : 1384 - 1392