On the learnability of rich function classes

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

This article is free to access.

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.

References Powered by Scopus

Fuzzy classifications using fuzzy inference networks

10281Citations
N/AReaders
Get full text

Pattern recognition and neural networks

4839Citations
N/AReaders
Get full text

A theory of the learnable

3670Citations
N/AReaders
Get full text

Register to see more suggestions

Mendeley helps you to discover research relevant for your work.

Already have an account?

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

Readers' Seniority

Tooltip

PhD / Post grad / Masters / Doc 9

56%

Professor / Associate Prof. 4

25%

Lecturer / Post doc 2

13%

Researcher 1

6%

Readers' Discipline

Tooltip

Computer Science 13

87%

Mathematics 1

7%

Engineering 1

7%

Save time finding and organizing research with Mendeley

Sign up for free