Personal tools
You are here: Home Publications Entropy Numbers for Convex Combinations and MLPs
Document Actions

A.J. Smola, A. Elisseeff, B. Sch\"olkopf, and R.C. Williamson (2000)

Entropy Numbers for Convex Combinations and MLPs

In: Advances in Large Margin Classifiers, ed. by A.J. Smola and P.L. Bartlett and B. Schölkopf and D. Schuurmans, pp. 369-388, Cambridge, MA, MIT Press.

Improved bounds on the entropy numbers of convex combinations of parameterized functions (such as combinations of classifiers) and compositions of these combinations (such as multi-layer neural networks) are given. In the latter case especially, the new bounds presented are substantially smaller than the previous results. They show that even more substantial improvements are possible when the parameterized functions involve kernels with rapidly decreasing eigenvalues. This gives the best known bounds for the covering numbers of radial basis function networks, for instance.

by admin last modified 2007-01-31 11:08

Powered by Plone CMS, the Open Source Content Management System