메뉴 건너뛰기




Volumn 7, Issue 4, 1996, Pages 953-968

Towards more practical average bounds on supervised learning

Author keywords

[No Author keywords available]

Indexed keywords

APPROXIMATION THEORY; COMPUTER SIMULATION; LEARNING ALGORITHMS; MATHEMATICAL MODELS; NEURAL NETWORKS; PERFORMANCE; REGRESSION ANALYSIS;

EID: 0030195241     PISSN: 10459227     EISSN: None     Source Type: Journal    
DOI: 10.1109/72.508938     Document Type: Article
Times cited : (10)

References (38)
  • 2
    • 0001024505 scopus 로고
    • On the uniform convergence of relative frequencies of events to their probabilities
    • V. N. Vapnik and A. Y. Chervonenkis, "On the uniform convergence of relative frequencies of events to their probabilities," Theory Probability Applicat., vol. 16, no. 2, pp. 264-280, 1971.
    • (1971) Theory Probability Applicat. , vol.16 , Issue.2 , pp. 264-280
    • Vapnik, V.N.1    Chervonenkis, A.Y.2
  • 4
    • 0027257001 scopus 로고
    • A universal theorem on learning curves
    • S. Amari, "A universal theorem on learning curves," Neural Networks, vol. 6, pp. 161-166, 1993.
    • (1993) Neural Networks , vol.6 , pp. 161-166
    • Amari, S.1
  • 5
    • 0000660569 scopus 로고
    • Four types of learning curves
    • S. Amari, N. Fujita, and S. Shinomoto, "Four types of learning curves," Neural Computa., vol. 4, no. 4, pp. 605-618, 1992.
    • (1992) Neural Computa. , vol.4 , Issue.4 , pp. 605-618
    • Amari, S.1    Fujita, N.2    Shinomoto, S.3
  • 6
    • 0006770566 scopus 로고
    • Estimating average-case learning curves using Bayesian, statistical physics, and VC dimension methods
    • D. Haussler, M. Kearns, M. Opper, and R. Schapire, "Estimating average-case learning curves using Bayesian, statistical physics, and VC dimension methods," Advances Neural Inform. Processing Syst., vol. 4, pp. 855-862, 1992.
    • (1992) Advances Neural Inform. Processing Syst. , vol.4 , pp. 855-862
    • Haussler, D.1    Kearns, M.2    Opper, M.3    Schapire, R.4
  • 8
    • 0025508916 scopus 로고
    • A statistical approach to learning and generalization in layered neural networks
    • E. Levin, N. Tishby, and S. Solla, "A statistical approach to learning and generalization in layered neural networks," Proc. IEEE, vol. 78, no. 10, pp. 1568-1574, 1990.
    • (1990) Proc. IEEE , vol.78 , Issue.10 , pp. 1568-1574
    • Levin, E.1    Tishby, N.2    Solla, S.3
  • 10
    • 0029410715 scopus 로고
    • On the practical applicability of VC dimension bounds
    • S. B. Holden and M. Niranjan, "On the practical applicability of VC dimension bounds," Neural Computa., vol. 7, no. 6, pp. 1265-1288, 1995.
    • (1995) Neural Computa. , vol.7 , Issue.6 , pp. 1265-1288
    • Holden, S.B.1    Niranjan, M.2
  • 11
    • 0001942829 scopus 로고
    • Neural networks and the bias/variance dilemma
    • S. Geman, E. Bienenstock, and R. Doursat, "Neural networks and the bias/variance dilemma," Neural Computa., vol. 4, no. 1, pp. 1-58, 1992.
    • (1992) Neural Computa. , vol.4 , Issue.1 , pp. 1-58
    • Geman, S.1    Bienenstock, E.2    Doursat, R.3
  • 12
    • 51249190305 scopus 로고
    • Statistical predictor identification
    • H. Akaike, "Statistical predictor identification," Ann. Inst. Statist. Math., vol. 22, pp. 203-217, 1970.
    • (1970) Ann. Inst. Statist. Math. , vol.22 , pp. 203-217
    • Akaike, H.1
  • 13
    • 0002167090 scopus 로고
    • Predicted squared error: A criterion for automatic model selection
    • S. Farlow, Ed. New York: Marcel Dekker
    • A. Barron, "Predicted squared error: A criterion for automatic model selection," in Self-Organizing Methods in Modeling, S. Farlow, Ed. New York: Marcel Dekker, 1984.
    • (1984) Self-Organizing Methods in Modeling
    • Barron, A.1
  • 15
    • 0000902690 scopus 로고
    • The effective number of parameters: An analysis of generalization and regularization in nonlinear learning systems
    • J. E. Moody, "The effective number of parameters: An analysis of generalization and regularization in nonlinear learning systems," Advances Neural Inform. Processing Syst., vol. 4, pp. 847-854, 1992.
    • (1992) Advances Neural Inform. Processing Syst. , vol.4 , pp. 847-854
    • Moody, J.E.1
  • 16
    • 0000372206 scopus 로고
    • Bayesian model comparison and backprop nets
    • D. Mackay, "Bayesian model comparison and backprop nets," Advances Neural Inform. Processing Syst., vol. 4, pp. 839-846, 1992.
    • (1992) Advances Neural Inform. Processing Syst. , vol.4 , pp. 839-846
    • Mackay, D.1
  • 17
    • 0002192516 scopus 로고
    • Decision theoretic generalizations of the PAC model for neural nets and other learning applications
    • D. Haussler, "Decision theoretic generalizations of the PAC model for neural nets and other learning applications," Inform. Computa., vol. 100, pp. 78-150, 1992.
    • (1992) Inform. Computa. , vol.100 , pp. 78-150
    • Haussler, D.1
  • 19
    • 0021518106 scopus 로고
    • A theory of the learnable
    • L. G. Valiant, "A theory of the learnable," Comm. ACM, vol. 27, no. 11, pp. 1134-1142, 1984.
    • (1984) Comm. ACM , vol.27 , Issue.11 , pp. 1134-1142
    • Valiant, L.G.1
  • 20
    • 0000629975 scopus 로고
    • Cross-validation choice and assessment of statistical predictions
    • M. Stone, "Cross-validation choice and assessment of statistical predictions (with discussion)," J. Royal Statist. Soc. B, vol. 36, pp. 111-147, 1974.
    • (1974) J. Royal Statist. Soc. B , vol.36 , pp. 111-147
    • Stone, M.1
  • 26
    • 33747647033 scopus 로고
    • Learning from examples in large neural networks
    • H. Seung, H. Sompolinsky, and N. Tishby, "Learning from examples in large neural networks," Phys. Rev., vol. A45, pp. 6058-6091, 1992.
    • (1992) Phys. Rev. , vol.A45 , pp. 6058-6091
    • Seung, H.1    Sompolinsky, H.2    Tishby, N.3
  • 27
    • 0024861871 scopus 로고
    • Approximation by superpositions of a sigmoidal function
    • G. Cybenko, "Approximation by superpositions of a sigmoidal function," Math. Contr., Signals, Syst., vol. 2, no. 4, pp. 303-314, 1989.
    • (1989) Math. Contr., Signals, Syst. , vol.2 , Issue.4 , pp. 303-314
    • Cybenko, G.1
  • 28
    • 0024880831 scopus 로고
    • Multilayer feedforward networks are universal approximators
    • H. Hornik, M. Stinchcombe, and H. White, "Multilayer feedforward networks are universal approximators," Neural Networks, vol. 2, pp. 359-366, 1989.
    • (1989) Neural Networks , vol.2 , pp. 359-366
    • Hornik, H.1    Stinchcombe, M.2    White, H.3
  • 29
    • 0027599793 scopus 로고
    • Universal approximation bounds for superpositions of a sigmoidal function
    • A. Barron, "Universal approximation bounds for superpositions of a sigmoidal function," IEEE Trans. Inform. Theory, vol. 39, pp. 930-945, 1993.
    • (1993) IEEE Trans. Inform. Theory , vol.39 , pp. 930-945
    • Barron, A.1
  • 30
    • 0025670892 scopus 로고
    • The multilayer perceptron as an approximation to a Bayes optimal discriminant function
    • D. W. Ruck, S. K. Rogers, M. Kabrisky, M. E. Oxley, and B. W. Suter, "The multilayer perceptron as an approximation to a Bayes optimal discriminant function," IEEE Trans. Neural Networks, vol. 1, pp. 296-298, 1990.
    • (1990) IEEE Trans. Neural Networks , vol.1 , pp. 296-298
    • Ruck, D.W.1    Rogers, S.K.2    Kabrisky, M.3    Oxley, M.E.4    Suter, B.W.5
  • 31
    • 0025597157 scopus 로고
    • Neural network classification: A Bayesian interpretation
    • E. Wan, "Neural network classification: A Bayesian interpretation," IEEE Trans. Neural Networks, vol. 1, pp. 303-305, 1990.
    • (1990) IEEE Trans. Neural Networks , vol.1 , pp. 303-305
    • Wan, E.1
  • 33
    • 0000539898 scopus 로고
    • How tight are the Vapnik-Chervonenkis bounds?
    • D. Cohn and G. Tesauro, "How tight are the Vapnik-Chervonenkis bounds?" Neural Computa., vol. 4, pp. 249-269, 1992.
    • (1992) Neural Computa. , vol.4 , pp. 249-269
    • Cohn, D.1    Tesauro, G.2
  • 34
    • 0000646059 scopus 로고
    • Learning internal representations by error propagation
    • Cambridge, MA: MIT Press
    • D. E. Rumelhart, G. E. Hinton, and R. J. Williams, "Learning internal representations by error propagation," in Parallel Distributed Processing, vol. 1. Cambridge, MA: MIT Press, 1986, pp. 318-362.
    • (1986) Parallel Distributed Processing , vol.1 , pp. 318-362
    • Rumelhart, D.E.1    Hinton, G.E.2    Williams, R.J.3
  • 35
    • 0348054751 scopus 로고
    • Improving the generalizing capabilities of a backpropagation network
    • A. Namatame and Y. Kimata, "Improving the generalizing capabilities of a backpropagation network," Int. J. Neural Networks Res. Applicat., vol. 1, no. 2, pp. 86-94, 1989.
    • (1989) Int. J. Neural Networks Res. Applicat. , vol.1 , Issue.2 , pp. 86-94
    • Namatame, A.1    Kimata, Y.2
  • 36
    • 0000926506 scopus 로고
    • When networks disagree: Ensemble methods for hybrid neural networks
    • R. J. Mammone, Ed. New York: Chapman and Hall
    • M. P. Perrone and L. N. Cooper, "When networks disagree: Ensemble methods for hybrid neural networks," in Neural Networks Speech Image Processing, R. J. Mammone, Ed. New York: Chapman and Hall, 1993.
    • (1993) Neural Networks Speech Image Processing
    • Perrone, M.P.1    Cooper, L.N.2


* 이 정보는 Elsevier사의 SCOPUS DB에서 KISTI가 분석하여 추출한 것입니다.