A Geometrical Representation of M-P Neural Model and Its Applications
Affiliation:

  • Article
  • | |
  • Metrics
  • |
  • Reference [1]
  • |
  • Related [20]
  • |
  • Cited by [114]
  • | |
  • Comments
    Abstract:

    In this paper, a geometrical representation of M-P neural model is presented. From the representation,a clear visual picture and interpretation of the model can be seen. Two interesting applications based on the interpretation are discussed. They are (1) a new design principle of feedforward neural networks, and (2) a new proof of mapping abilities of three-layer feedforward neural networks.

    Reference
    1  McCulloch W S, Pitts W. A logical calculus of the ideas immanent in nervous activity. Bulletin of Mathematical Biophysics, 1943,5:115~133 2  Rujan P, Marchand M. A geometric approach to learning in neural networks. In: Proceedings of the International Joint Conference on Neural Networks'89, Vol II. Washington, DC: IEEE TAB Neural Network Committee, 1989. 105~110 3  Ramacher U, Wesseling M. A geometrical approach to neural neywork design. In: Proceedings of the International Joint Conference on Neural Networks'89, Vol II. Washington, DC: IEEE TAB Neural Network Committee, 1989. 147~154 4  Rumelhart D E, McClelland J L. Parallel distributed processing(Vol.1~2). Cambridge, MA: MIT Press, 1986 5  张铃,张钹.多层前馈神经网络的综合和学习算法.软件学报,1997,8(4):252~258 (Zhang Ling, Zhang Bo. A forward propagation learning algorithm of multilayered neural networks with feedback connections. Journal of Software, 1997,8(4):252~258) 6  Funabashi K. On the approximate realization of continuous mappings by neural networks. Neural Networks, 1989,2:183~192 7  Arai M. Mapping abilities of three-layer neural networks. In: Proceedings of the International Joint Conference on Neural Networks'89, Vol I. Washington, DC: IEEE TAB Neural Network Committee, 1989. 419~423 8  Hecht-Nielsen R. Theory of the backpropagation neural networks. In: Proceedings of the International Joint Conference on Neural Networks'89, Vol I. Washington, DC: IEEE TAB Neural Network Committee, 1989. 593~605
    Comments
    Comments
    分享到微博
    Submit
Get Citation

张铃,张钹. M-P神经元模型的几何意义及其应用.软件学报,1998,9(5):334-338

Copy
Share
Article Metrics
  • Abstract:10399
  • PDF: 7246
  • HTML: 0
  • Cited by: 0
History
  • Received:November 06,1997
  • Revised:February 25,1998
You are the first2045176Visitors
Copyright: Institute of Software, Chinese Academy of Sciences Beijing ICP No. 05046678-4
Address:4# South Fourth Street, Zhong Guan Cun, Beijing 100190,Postal Code:100190
Phone:010-62562563 Fax:010-62562533 Email:jos@iscas.ac.cn
Technical Support:Beijing Qinyun Technology Development Co., Ltd.

Beijing Public Network Security No. 11040202500063