On the learnability of rich function classes

0Citations
Citations of this article
17Readers
Mendeley users who have this article in their library.

Abstract

The probably approximately correct (PAC) model of learning and its extension to real-valued function classes sets a rigorous framework based upon which the complexity of learning a target from a function class using a finite sample can be computed. There is one main restriction, however, that the function class have a finite VC-dimension or scale-sensitive pseudo-dimension. In this paper we present an extension of the PAC framework with which rich function classes with possibly infinite pseudo-dimension may be learned with a finite number of examples and a finite amount of partial information. As an example we consider learning a family of infinite dimensional Sobolev classes. © 1999 Academic Press.

Cite

CITATION STYLE

APA

Ratsaby, J., & Maiorov, V. (1999). On the learnability of rich function classes. Journal of Computer and System Sciences, 58(1), 183–192. https://doi.org/10.1006/jcss.1998.1604

Register to see more suggestions

Mendeley helps you to discover research relevant for your work.

Already have an account?

Save time finding and organizing research with Mendeley

Sign up for free