Abstract
We study a parametric estimation problem. Our aim is to estimate or to identify the conditional probability which is called the system. We suppose that we can select appropriate inputs to the system when we gather the training data. This kind of estimation is called active learning in the context of the artificial neural networks. In this paper we suggest new active learning algorithms and evaluate the risk of the algorithms by using statistical asymptotic theory. The algorithms are regarded as a version of the experimental design with two-stage sampling. We verify the efficiency of the active learning by simple computer simulations.
Similar content being viewed by others
References
Belue, L. M., Bauer, K. W., Jr. and Ruck, D. W. (1997). Selecting optimal experiments for multiple output multilayer perceptrons, Neural Computation, 9, 161–183.
Bishop C. M. (1995). Neural Networks for Pattern Recognition, Oxford University Press, New York.
Chaloner, K. and Verdinelli, I. (1995). Bayesian experimental design: A review, Statist. Sci., 10, 273–304.
Fedorov, V. V. (1972). Theory of Optimal Experiments, Academic Press, New York.
Ford, I., Titterington, D. M. and Kitsos, C. P. (1989). Recent advances in nonlinear experimental designs, Technometrics, 31, 49–60
Fukumizu, K. (1996). Active learning in multilayer perceptrons, Advances in Neural Information Processing Systems (ed. D. S. Touretzky, M. C Mozer and M. E. Hasselmo), 8, 295–301, MIT Press, Cambridge, Massachusetts.
MacKay, D. (1992). Information-based objective function for active data selection, Neural Computation, 4, 305–318
Pukelsheim F. (1993). Optimal Design of Experiments, Wiley, New York.
Silvey, D. S. (1980). Optimal Design, Monographs on Applied Probability and Statistics, Chapman and Hall, London.
Watkin, T. L. H. and Rau, A. (1992). Selecting examples for perceptrons, Journal of Physics A: Mathematical and General, 25, 113–121.
White, H. (1982). Maximum likelihood estimation of misspecified models, Econometrica, 50, 1–25.
Author information
Authors and Affiliations
About this article
Cite this article
Kanamori, T. Statistical Asymptotic Theory of Active Learning. Annals of the Institute of Statistical Mathematics 54, 459–475 (2002). https://doi.org/10.1023/A:1022446624428
Issue Date:
DOI: https://doi.org/10.1023/A:1022446624428