Title

Concept learning by example decomposition

Authors

Authors

S. Joshi

Comments

Authors: contact us about adding a copy of your work at STARS@ucf.edu

Abbreviated Journal Title

J. Exp. Theor. Artif. Intell.

Keywords

concept learning; example decomposition; concept decomposition; probably; approximately correct; computational learning theory; learning by; decomposition; FEATURE-EXTRACTION; MODEL; Computer Science, Artificial Intelligence

Abstract

It is widely accepted in machine learning that it is easier to learn several smaller decomposed concepts than a single large one. Typically, such decomposition of concepts is achieved in highly constrained environments, or aided by human experts. In this article, we investigate concept learning by example decomposition in a general probably approximately correct setting for Boolean learning. We develop sample complexity bounds for the different steps involved in the process. We formally show that if the cost of example partitioning is kept low then it is highly advantageous to learn by example decomposition.

Journal Title

Journal of Experimental & Theoretical Artificial Intelligence

Volume

22

Issue/Number

1

Publication Date

1-1-2010

Document Type

Article

Language

English

First Page

1

Last Page

21

WOS Identifier

WOS:000274673700001

ISSN

0952-813X

Share

COinS