×

Three fundamental concepts of the capacity of learning machines. (English) Zbl 0799.60032

Summary: We present three fundamental concepts concerning the capacity of learning machines which describe necessary and sufficient conditions of consistency of the learning processes and the bounds of the rate of convergence of the learning processes both for the distribution dependent case and the distribution independent case.

MSC:

60F99 Limit theorems in probability theory
PDFBibTeX XMLCite
Full Text: DOI

References:

[1] Vapnik, V. N.; Chervonenkis, A. J., Pattern Recognit. Image Anal., 283-305 (1991)
[2] Vapnik, V. N.; Chervonenkis, A. J., Theor. Prob. Appl., 26, 265-280 (1981)
[3] Vapnik, V. N.; Chervonenkis, A. J., Theor. Prob. Appl., 16, 532-553 (1971)
[4] Vapnik, V. N., Estimation of Dependences Based on Empirical Data (1982), Springer: Springer New York · Zbl 0499.62005
This reference list is based on information provided by the publisher or from digital mathematics libraries. Its items are heuristically matched to zbMATH identifiers and may contain data conversion errors. In some cases that data have been complemented/enhanced by data from zbMATH Open. This attempts to reflect the references listed in the original paper as accurately as possible without claiming completeness or a perfect matching.