论文信息 - Estimating Average-Case Learning Curves Using Bayesian, Statistical Physics and VC Dimension Methods - 字舞流文

Estimating Average-Case Learning Curves Using Bayesian, Statistical Physics and VC Dimension Methods

In this paper we investigate an average-case model of concept learning, and give results that place the popular statistical physics and VC dimension theories of learning curve behavior in a common framework.

David Haussler | Manfred Opper | Robert E. Schapire | Michael Kearns

[1] David Haussler,et al. What Size Net Gives Valid Generalization? , 1989, Neural Computation.

[2] David Haussler,et al. Predicting {0,1}-functions on randomly drawn points , 1988, COLT '88.

[3] Sompolinsky,et al. Learning from examples in large neural networks. , 1990, Physical review letters.

[4] David Haussler,et al. Bounds on the sample complexity of Bayesian learning using information theory and the VC dimension , 1991, COLT '91.

[5] Naftali Tishby,et al. Consistent inference of probabilities in layered networks: predictions and generalizations , 1989, International 1989 Joint Conference on Neural Networks.

[6] Norbert Sauer,et al. On the Density of Families of Sets , 1972, J. Comb. Theory A.

[7] Lawrence D. Jackel,et al. Large Automatic Learning, Rule Extraction, and Generalization , 1987, Complex Syst..

[8] Vladimir Vapnik,et al. Chervonenkis: On the uniform convergence of relative frequencies of events to their probabilities , 1971 .

[9] David Haussler,et al. Calculation of the learning curve of Bayes optimal classification algorithm for learning a perceptron with noise , 1991, COLT '91.