Learning Curves: Asymptotic Values and Rate of Convergence

Part of Advances in Neural Information Processing Systems 6 (NIPS 1993)

Bibtex Metadata Paper


Corinna Cortes, L. D. Jackel, Sara Solla, Vladimir Vapnik, John Denker


Training classifiers on large databases is computationally demand(cid:173) ing. It is desirable to develop efficient procedures for a reliable prediction of a classifier's suitability for implementing a given task, so that resources can be assigned to the most promising candidates or freed for exploring new classifier candidates. We propose such a practical and principled predictive method. Practical because it avoids the costly procedure of training poor classifiers on the whole training set, and principled because of its theoretical foundation. The effectiveness of the proposed procedure is demonstrated for both single- and multi-layer networks.