On the Fault Tolerance Problem of the Feedforward Neural Networks
Affiliation:

  • Article
  • | |
  • Metrics
  • |
  • Reference [17]
  • |
  • Related [20]
  • |
  • Cited by [1]
  • | |
  • Comments
    Abstract:

    Until recently, in the literatures of discussing the fault tolerance problem of neural networks, the tolerance about input noise is mainly concerned. The problem is generally transformed into that of optimization and solved by some well-known optimization approach. But only a few dealt with the tolerance due to the network structural failure, i.e., the structural fault tolerance. In the paper, the structural fault tolerance is analyzed by using the covering algorithms. The necessary and sufficient conditions of allowing of single node failure in a neural network and the algorithm for constructing such a network are given. These results reveal the essence of the structural fault tolerance capacity and show a new way for the analysis of the fault tolerance of neural networks.

    Reference
    [1] Hammadi, N.C., Ito, H. A learning algorithm for fault tolerant feedforward neural networks. IEICE Transactions on Information and Systems, 1997,E80-D(1):21~27.
    [2] Minnix, J.I. Fault tolerance of backpropagation neural network trained on noise inputs. In: Proceedings of the International Joint Conference on Neural Networks. New York: IEEE Press, 1992. 847~852.
    [3] Murray, A.F., Edwards, P.J. Enhanced MLP performance and fault-tolerance resulting from synaptic weight noise during training. IEEE Transactions on Neural Networks, 1994,5(5):792~802.
    [4] Emmerson, M.D., Damper, R.I. Determining and improving the fault-tolerance of multilayer perceptions in a pattern-recognition application. IEEE Transactions on Neural Networks, 1993,4(5):788~793.
    [5] Phatak, D.S., Koren, I. Complete and partial fault tolerance of feedforward neural nets. IEEE Transactions on Neural Networks, 1995,6(2):446~456.
    [6] Chiru, C.T., Mehrotra, K., Mohan, C.K., et al. Training techniques to obtain fault-tolerant neural networks. In: Proceedings of the International Symposium on Fault-Tolerant Computing. New York: IEEE Press, 1994. 360~369.
    [7] Rumelhart, D., Hinton, G., Williams, R. Learning representations by backpropagating errors. Nature, 1986,323(9):318~362.
    [8] Tan, Y., Nanya, T. Fault-Tolerant back-propagation model and its generation ability. In: Proceedings of the International Joint Conference on Neural Networks. New York: IEEE Press, 1993. 2516~2519.
    [9] Neti, C., Schneider, M.H., Young, E.D. Maximally fault-tolerant neural networks. IEEE Transactions on Neural Networks, 1992,3(1):14~23.
    [10] Deodhare, D., Vidyasagar, M., Keerthi, S.S. Synthesis of fault-tolerant feedforward neural networks using minimax optimization. IEEE Transactions on Neural Networks, 1998,9(5):891~900.
    [11] Nijhuis, J., Hofflinger, B., Schaik, A., et al. Limits to fault-tolerance of a feedforward neural network with learning. In: Proceedings of the International Symposium on Fault-Tolerant Computing. New York: IEEE Press, 1990. 228~235.
    [12] Zhang, L., Zhang, B. A geometrical representation of McCulloch-Pitts neural model and its applications. IEEE Transactions on Neural Networks, 1999,10(4):925~929.
    [13] 张铃,张钹.多层前馈网络的学习和综合算法.软件学报,1995,6(7):440~448.Zhang, L., Zhang, B. A Learning and synthesis algorithm of multilayered feedforward neural networks. Journal of Software, 1995,6(7):440~448 (in Chinese).
    [14] Rujan, P., Marchand, M. A geometric approach to learning in neural networks. In: Proceedings of the International Joint Conference on Neural Networks'89. Washington, DC: IEEE Press, 1989. 105~110.
    [15] Ramacher, U., Wesseling, M. A geometrical approach to neural network design. In: Proceedings of the International Joint Conference on Neural Networks'89. Washington, DC: IEEE Press, 1989. 147~154.
    [16] Funabashi, K. On the approximate realization of continuous mappings by neural networks. Neural Networks, 1989,2(1):183~192.
    [17] Arai, M. Mapping abilities of three-layer neural networks. In: Proceedings of the International Joint Conference on Neural Networks'89. Washington, DC: IEEE Press, 1989. 419~423.
    Comments
    Comments
    分享到微博
    Submit
Get Citation

张铃.前向神经网络的容错性问题.软件学报,2001,12(11):1693-1398

Copy
Share
Article Metrics
  • Abstract:
  • PDF:
  • HTML:
  • Cited by:
History
  • Received:March 03,2000
  • Revised:June 26,2000
You are the first2032648Visitors
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