메뉴 건너뛰기




Volumn 31, Issue 1-4, 2000, Pages 87-103

Improving the tolerance of multilayer perceptrons by minimizing the statistical sensitivity to weight deviations

Author keywords

ANOVA; Backpropagation; Fault tolerance; Statistical sensitivity; Weight deviations

Indexed keywords

BACKPROPAGATION; FAULT TOLERANT COMPUTER SYSTEMS; FEEDFORWARD NEURAL NETWORKS; LEARNING ALGORITHMS; SENSITIVITY ANALYSIS; STATISTICAL METHODS;

EID: 0034058275     PISSN: 09252312     EISSN: None     Source Type: Journal    
DOI: 10.1016/S0925-2312(99)00150-2     Document Type: Article
Times cited : (34)

References (27)
  • 2
    • 21744454478 scopus 로고    scopus 로고
    • A modified backpropagation algorithm to tolerate weight errors
    • Springer, Berlin
    • J.L. Bernier, J. Ortega, A. Prieto, A modified backpropagation algorithm to tolerate weight errors, Lecture Notes in Computer Science, Vol. 1240, Springer, Berlin, 1997, pp. 763-771.
    • (1997) Lecture Notes in Computer Science , vol.1240 , pp. 763-771
    • Bernier, J.L.1    Ortega, J.2    Prieto, A.3
  • 6
    • 0026625982 scopus 로고
    • Sensitivity analysis of multilayer perceptron with differentiable activation functions
    • Choi J.Y., Choi C. Sensitivity analysis of multilayer perceptron with differentiable activation functions. IEEE Trans. Neural Networks. 3(1):1992;101-107.
    • (1992) IEEE Trans. Neural Networks , vol.3 , Issue.1 , pp. 101-107
    • Choi, J.Y.1    Choi, C.2
  • 7
    • 0029440452 scopus 로고
    • Can deterministic penalty terms model the effects of synaptic weight noise on network fault-tolerance?
    • Edwards P.J., Murray A.F. Can deterministic penalty terms model the effects of synaptic weight noise on network fault-tolerance? Int. J. Neural Systems. 6(4):1995;401-416.
    • (1995) Int. J. Neural Systems , vol.6 , Issue.4 , pp. 401-416
    • Edwards, P.J.1    Murray, A.F.2
  • 10
    • 0001622106 scopus 로고
    • The comparison of samples with possibly unequal variances
    • Fisher R.A. The comparison of samples with possibly unequal variances. Ann. Eugenics. 9:1936;174-180.
    • (1936) Ann. Eugenics , vol.9 , pp. 174-180
    • Fisher, R.A.1
  • 11
    • 0343962409 scopus 로고
    • Optimization Toolbox
    • (The MathWorks Inc.
    • A. Grace, Optimization Toolbox, in: Matlab Users Guide (The MathWorks Inc., 1994).
    • (1994) In: Matlab Users Guide
    • Grace, A.1
  • 12
    • 0001219859 scopus 로고
    • Regularization theory and neural networks architectures
    • Girosi F., Jones M., Poggio T. Regularization theory and neural networks architectures. Neural Computat. 7:1995;219-269.
    • (1995) Neural Computat. , vol.7 , pp. 219-269
    • Girosi, F.1    Jones, M.2    Poggio, T.3
  • 13
    • 84931162639 scopus 로고
    • The condensed nearest neighbor rule
    • P.E. Hart, The condensed nearest neighbor rule, IEEE Trans Inform. Theory 125 (1968) 515-516.
    • (1968) IEEE Trans Inform. Theory , vol.125 , pp. 515-516
    • Hart, P.E.1
  • 17
    • 0023331258 scopus 로고
    • An introduction to computing with neural nets
    • R.P. Lippmann, An introduction to computing with neural nets, IEEE ASSP Mag. (1987) 4-22.
    • (1987) IEEE ASSP Mag. , pp. 4-22
    • Lippmann, R.P.1
  • 18
    • 0038906922 scopus 로고
    • Regularization techniques in artificial neural networks, World Congr.
    • J. Mao, A.K. Jain, Regularization techniques in artificial neural networks, World Congr. Neural Networks 4 (1993) 75-79.
    • (1993) Neural Networks , vol.4 , pp. 75-79
    • Mao, J.1    Jain, A.K.2
  • 20
    • 0028494739 scopus 로고
    • Synaptic weight noise during MLP training: Enhanced MLP performance and fault tolerance resulting from synaptic weight noise during training
    • Murray A.F., Edwards P.J. Synaptic weight noise during MLP training: enhanced MLP performance and fault tolerance resulting from synaptic weight noise during training. IEEE Trans. Neural Networks. 5(5):1994;792-802.
    • (1994) IEEE Trans. Neural Networks , vol.5 , Issue.5 , pp. 792-802
    • Murray, A.F.1    Edwards, P.J.2
  • 22
    • 0029269583 scopus 로고
    • Complete and partial fault tolerance of feedforward neural nets
    • Pathak D.S., Koren I. Complete and partial fault tolerance of feedforward neural nets. IEEE Trans. Neural Networks. 6(2):1995;446-456.
    • (1995) IEEE Trans. Neural Networks , vol.6 , Issue.2 , pp. 446-456
    • Pathak, D.S.1    Koren, I.2
  • 23
    • 0028532748 scopus 로고
    • Comparative fault tolerance of parallel distributed processing networks
    • Segee B.E., Carter M.J. Comparative fault tolerance of parallel distributed processing networks. IEEE Trans. Comput. 43(11):1994;1323-1329.
    • (1994) IEEE Trans. Comput. , vol.43 , Issue.11 , pp. 1323-1329
    • Segee, B.E.1    Carter, M.J.2
  • 25
    • 0028375326 scopus 로고
    • Interpolation, completion, and learning fuzzy rules
    • Sudkamp T., Hammell R. Interpolation, completion, and learning fuzzy rules. IEEE Trans. Systems, Man Cybern. 24(2):1994;332-342.
    • (1994) IEEE Trans. Systems, Man Cybern. , vol.24 , Issue.2 , pp. 332-342
    • Sudkamp, T.1    Hammell, R.2
  • 26
    • 0003472433 scopus 로고
    • Design and Stability Analysis, Prentice-Hall, Englewood Cliffs, NJ
    • L. Wang, Adaptive Fuzzy Systems and Control. Design and Stability Analysis, Prentice-Hall, Englewood Cliffs, NJ, 1994.
    • (1994) Adaptive Fuzzy Systems and Control
    • Wang, L.1
  • 27
    • 0343962408 scopus 로고    scopus 로고
    • The learning capability of cyclic activation BP for two-spirals problem
    • T. Yoshino, I. Nagayama, N. Akamatsu, The learning capability of cyclic activation BP for two-spirals problem, Proceedings of IIZUKA'96, 1996, pp. 684-687.
    • (1996) Proceedings of IIZUKA'96 , pp. 684-687
    • Yoshino, T.1    Nagayama, I.2    Akamatsu, N.3


* 이 정보는 Elsevier사의 SCOPUS DB에서 KISTI가 분석하여 추출한 것입니다.