Consistency of posterior distributions for neural networks

Neural Networks

Volumn 13, Issue 6, 2000, Pages 629-642

  Lee, H K H ^a  

^a DUKE UNIVERSITY   (United States)

Author keywords

Asymptotic consistency; Bayesian statistics; Bracketing entropy; Hellinger distance; Nonparametric regression; Posterior approximation; Sieve asymptotics

Indexed keywords

ASYMPTOTIC STABILITY; MARKOV PROCESSES; MATHEMATICAL MODELS; MAXIMUM LIKELIHOOD ESTIMATION; MONTE CARLO METHODS; PROBABILITY DENSITY FUNCTION; PROBABILITY DISTRIBUTIONS; REGRESSION ANALYSIS; STATISTICS;

ASYMPTOTIC CONSISTENCY; BAYESIAN STATISTICS; HELLINGER DISTANCE; POSTERIOR DISTRIBUTION;

FEEDFORWARD NEURAL NETWORKS;

ARTICLE; ARTIFICIAL NEURAL NETWORK; BAYES THEOREM; MATHEMATICAL ANALYSIS; MATHEMATICAL COMPUTING; PRIORITY JOURNAL; REGRESSION ANALYSIS; STATISTICAL ANALYSIS;

BAYES THEOREM; NEURAL NETWORKS (COMPUTER); REGRESSION ANALYSIS;

EID: 0034233266     PISSN: 08936080     EISSN: None     Source Type: Journal    
DOI: 10.1016/S0893-6080(00)00045-9     Document Type: Article

References (20)

1. Barron A., Schervish M.J., Wasserman L. The consistency of posterior distributions in nonparametric problems. Annals of Statistics. 10:1999;536-561.
2. Bishop C.M. Neural networks for pattern recognition. 1995;Clarendon Press, Oxford, UK.
3. Buntine W.L., Weigend A.S. Bayesian back-propagation. Complex Systems. 5:1991;603-643.
4. Diaconis P., Freedman D.A. On the consistency of Bayes estimates. Annals of Statistics. 14:1986;1-26.
5. Doob, J. L. (1949). Application of the theory of martingales. Le Calcul des Probabilites et ses Applications (pp. 23-27). Colloque Internationaux du Centre National de la Recherche Scientifique: Paris.
6. Funahashi K. On the approximate realization of continuous mappings by neural networks. Neural Networks. 2:1989;183-192.
7. Gelman A., Carlin J.B., Stern H.S., Rubin D.B. Bayesian data analysis. 1995;Chapman and Hall, London.
8. Gilks W.R., Richardson S., Spiegelhalter D.J. Markov Chain Monte Carlo in practice. 1996;Chapman and Hall, London.
9. Haussler D., Opper M. Metric entropy and minimax risk in classification. Mycielski J., Rozenberg G., Salomaa A. Studies in logic and computer science. Lecture notes in computer science. vol. 1261:1997;212-235 Springer, New York.
10. Hornik K., Stinchcombe M., White H. Multilayer feedforward networks are universal approximators. Neural Networks. 2:1989;359-366.
11. Krogh A., Hertz J.A. A simple weight decay can improve generalization. Moody J.E., Hanson S.J., Lippman R.P. Advances in neural information processing systems. vol. 4:1992;MIT Press, Campridge, MA.
12. Lee, H. K. H. (1998). Model selection and model averaging for neural networks. PhD thesis. Department of Statistics, Carnegie Mellon University.
13. MacKay, D. J. C. (1992). Bayesian methods for adaptive methods. PhD thesis. California Institute of Technology.
14. Müller P., Rios Insua D. Feedforward neural networks for nonparametric regression. Dey D., Müller P., Sinha D. Practical nonparametric and semiparametric Bayesian statistics. 1998;Springer, New York. pp. 181-193.
15. Müller P., Rios Insua D. Issues in Bayesian analysis of neural network models. Neural Computation. 10:1998;571-592.
16. Neal R.M. Bayesian learning for neural networks. 1996;Springer, New York.
17. Pollard D. Bracketing methods in statistics and econometrics. Barnett W.A., Powell J., Tauchen G.E. Nonparametric and semiparametric methods in econometrics and statistics. : Proceedings of the Fifth International Symposium in Econometric Theory and Econometrics. 1991;337-355 Cambridge University Press, Cambridge, UK.
18. van der Vaart A.W., Wellner J.A. Weak convergence and empirical processes. 1996;Springer, New York.
19. Wasserman L. Asymptotic properties of nonparametric Bayesian procedures. Dey D., Müller P., Sinha D. Practical nonparametric and semiparametric Bayesian statistics. 1998;Springer, New York. pp. 293-304.
20. Wong W.H., Shen X. Probability inequalities for likelihood ratios and convergence rates of sieve mles. Annals of Statistics. 23:1995;339-362.