Welcome to IEEE Xplore 2.0: PAC learning with generalized samples and an applicaiton tostochastic geometry

Cart | Sitemap | Help

Abstract


	BROWSE	SEARCH	IEEE XPLORE GUIDE	SUPPORT

View TOC

PAC learning with generalized samples and an applicaiton tostochastic geometry

Kulkarni, S.R. Mitter, S.K. Tsitsiklis, J.N. Zeitouni, O.
MIT, Cambridge, MA;

This paper appears in: Pattern Analysis and Machine Intelligence, IEEE Transactions on
Publication Date: Sep 1993
Volume: 15, Issue: 9
On page(s): 933-942
ISSN: 0162-8828
References Cited: 24
CODEN: ITPIDJ
INSPEC Accession Number: 4526022
Digital Object Identifier: 10.1109/34.232080
Posted online: 2002-08-06 18:43:51.0

Abstract
An extension of the standard probably approximately correct (PAC) learning model that allows the use of generalized samples is introduced. A generalized sample is viewed as a pair consisting of a functional on the concept class together with the value obtained by the functional operating on the unknown concept. It appears that this model can be applied to a number of problems in signal processing and geometric reconstruction to provide sample size bounds under a PAC criterion. A specific application of the generalized model to a problem of curve reconstruction is considered, and some connections with a result from stochastic geometry are discussed

Index Terms
Available to subscribers and IEEE members.

References
Available to subscribers and IEEE members.

Citing Documents
Available to subscribers and IEEE members.