메뉴 건너뛰기




Volumn 31, Issue 3, 2003, Pages 833-851

Likelihood ratio of unidentifiable models and multilayer neural networks

Author keywords

Likelihood ratio; Locally conic model; Multilayer neural networks; Unidentifiable model

Indexed keywords


EID: 0042311289     PISSN: 00905364     EISSN: None     Source Type: Journal    
DOI: 10.1214/aos/1056562464     Document Type: Article
Times cited : (47)

References (19)
  • 1
    • 0001940707 scopus 로고
    • Asymptotic distribution of the likelihood ratio statistic in a prototypical nonregular problem
    • (J. K. Ghosh, S. K. Mitra, K. R. Parthasarathy and B. P. Rao, eds.). Wiley Eastern, New Delhi
    • BICKEL, P. and CHERNOFF, H. (1993). Asymptotic distribution of the likelihood ratio statistic in a prototypical nonregular problem. In Statistics and Probability: A Raghu Raj Bahadur Festschrift (J. K. Ghosh, S. K. Mitra, K. R. Parthasarathy and B. P. Rao, eds.) 83-96. Wiley Eastern, New Delhi.
    • (1993) Statistics and Probability: A Raghu Raj Bahadur Festschrift , pp. 83-96
    • Bickel, P.1    Chernoff, H.2
  • 4
    • 84996128633 scopus 로고    scopus 로고
    • Testing in locally conic models and application to mixture models
    • DACUNHA-CASTELLE, D. and GASSIAT, E. (1997). Testing in locally conic models and application to mixture models. ESAIM Probab. Statist. 1 285-317.
    • (1997) ESAIM Probab. Statist. , vol.1 , pp. 285-317
    • Dacunha-Castelle, D.1    Gassiat, E.2
  • 5
    • 0033236920 scopus 로고    scopus 로고
    • Testing the order of a model using locally conic parametrization: Population mixtures and stationary ARMA processes
    • DACUNHA-CASTELLE, D. and GASSIAT, E. (1999). Testing the order of a model using locally conic parametrization: Population mixtures and stationary ARMA processes. Ann. Statist. 27 1178-1209.
    • (1999) Ann. Statist. , vol.27 , pp. 1178-1209
    • Dacunha-Castelle, D.1    Gassiat, E.2
  • 6
    • 0030198493 scopus 로고    scopus 로고
    • A regularity condition of the information matrix of a multilayer perception network
    • FUKUMIZU, K. (1996). A regularity condition of the information matrix of a multilayer perception network. Neural Networks 9 871-879.
    • (1996) Neural Networks , vol.9 , pp. 871-879
    • Fukumizu, K.1
  • 7
    • 84957085126 scopus 로고    scopus 로고
    • Generalization error of linear neural networks in unidentifiable cases
    • (O. Watanabe and T. Yokomori, eds.). Springer, Berlin
    • FUKUMIZU, K. (1999). Generalization error of linear neural networks in unidentifiable cases. In Algorithmic Learning Theory. Lecture Notes in Artificial Intelligence (O. Watanabe and T. Yokomori, eds.) 1720 51-62. Springer, Berlin.
    • (1999) Algorithmic Learning Theory. Lecture Notes in Artificial Intelligence , vol.1720 , pp. 51-62
    • Fukumizu, K.1
  • 8
    • 0034018074 scopus 로고    scopus 로고
    • Local minima and plateaus in hierarchical structures of multilayer perceptions
    • FUKUMIZU, K. and AMARI, S. (2000). Local minima and plateaus in hierarchical structures of multilayer perceptions. Neural Networks 13 317-327.
    • (2000) Neural Networks , vol.13 , pp. 317-327
    • Fukumizu, K.1    Amari, S.2
  • 9
    • 0034454408 scopus 로고    scopus 로고
    • The likelihood ratio test for the number of components in a mixture with Markov regime
    • GASSIAT, E. and KÉRIBIN, C. (2000). The likelihood ratio test for the number of components in a mixture with Markov regime. ESAIM Probab. Statist. 4 25-52.
    • (2000) ESAIM Probab. Statist. , vol.4 , pp. 25-52
    • Gassiat, E.1    Kéribin, C.2
  • 10
    • 0033698411 scopus 로고    scopus 로고
    • On the problem in model selection of neural network regression in overrealizable scenario
    • IEEE Comput. Soc., Los Alamitos, CA
    • HAGIWARA, K., KUNO, K. and USUI, S. (2000). On the problem in model selection of neural network regression in overrealizable scenario. In Proc. IEEE-INNS-ENNS International Joint Conference on Neural Networks 6 461-466. IEEE Comput. Soc., Los Alamitos, CA.
    • (2000) Proc. IEEE-INNS-ENNS International Joint Conference on Neural Networks , vol.6 , pp. 461-466
    • Hagiwara, K.1    Kuno, K.2    Usui, S.3
  • 11
    • 0000881495 scopus 로고
    • A failure of likelihood asymptotics for normal mixtures
    • (L. M. Le Cam and R. A. Olshen, eds.). Wadsworth, Belmont, CA
    • HARTIGAN, J. A. (1985). A failure of likelihood asymptotics for normal mixtures. In Proc. Berkeley Conference in Honor of Jerzy Neyman and Jack Kiefer (L. M. Le Cam and R. A. Olshen, eds.) 2 807-810. Wadsworth, Belmont, CA.
    • (1985) Proc. Berkeley Conference in Honor of Jerzy Neyman and Jack Kiefer , vol.2 , pp. 807-810
    • Hartigan, J.A.1
  • 12
    • 0029706958 scopus 로고    scopus 로고
    • On the least square error and prediction square error of function representation with discrete variable basis
    • IEEE, New York
    • HAYASAKA, T., TODA, N., USUI, S. and HAGIWARA, K. (1996). On the least square error and prediction square error of function representation with discrete variable basis. In Proc. Conference on Neural Networks for Signal Processing 6 72-81. IEEE, New York.
    • (1996) Proc. Conference on Neural Networks for Signal Processing , vol.6 , pp. 72-81
    • Hayasaka, T.1    Toda, N.2    Usui, S.3    Hagiwara, K.4
  • 13
    • 0010191129 scopus 로고
    • On the assumptions used to prove asymptotic normality of maximum likelihood estimates
    • LE CAM, L. (1970). On the assumptions used to prove asymptotic normality of maximum likelihood estimates. Ann. Math. Statist. 41 802-828.
    • (1970) Ann. Math. Statist. , vol.41 , pp. 802-828
    • Le Cam, L.1
  • 15
    • 0000646059 scopus 로고
    • Learning internal representations by error propagation
    • (D. E. Rumelhart, J. L. McClelland and the PDP Research Group, eds.). MIT Press, Cambridge, MA
    • RUMELHART, D. E., HINTON, G. E. and WILLIAMS, R. J. (1986). Learning internal representations by error propagation. In Parallel Distributed Processing (D. E. Rumelhart, J. L. McClelland and the PDP Research Group, eds.) 1 318-362. MIT Press, Cambridge, MA.
    • (1986) Parallel Distributed Processing , vol.1 , pp. 318-362
    • Rumelhart, D.E.1    Hinton, G.E.2    Williams, R.J.3
  • 16
    • 0000838588 scopus 로고
    • On the multi-dimensional central limit theorem
    • SAZONOV, V. V. (1968). On the multi-dimensional central limit theorem. Sankhyā Ser. A 30 181-204.
    • (1968) Sankhyā Ser. A , vol.30 , pp. 181-204
    • Sazonov, V.V.1
  • 17
    • 0026897370 scopus 로고
    • Uniqueness of the weights for minimal feedforward nets with a given input-output map
    • SUSSMANN, H. J. (1992). Uniqueness of the weights for minimal feedforward nets with a given input-output map. Neural Networks 5 589-593.
    • (1992) Neural Networks , vol.5 , pp. 589-593
    • Sussmann, H.J.1
  • 18
    • 84986754953 scopus 로고
    • Asymptotic distributions of likelihood ratios for overparameterized ARMA processes
    • VERES, S. (1987). Asymptotic distributions of likelihood ratios for overparameterized ARMA processes. J. Time Ser. Anal. 8 345-357.
    • (1987) J. Time Ser. Anal. , vol.8 , pp. 345-357
    • Veres, S.1
  • 19
    • 0000167944 scopus 로고
    • Note on the consistency of the maximum likelihood estimate
    • WALD, A. (1949). Note on the consistency of the maximum likelihood estimate. Ann. Math. Statist. 20 595-601.
    • (1949) Ann. Math. Statist. , vol.20 , pp. 595-601
    • Wald, A.1


* 이 정보는 Elsevier사의 SCOPUS DB에서 KISTI가 분석하여 추출한 것입니다.