PAC learning with generalized samples and an applicaiton to stochastic geometry

Author

Kulkarni, Sanjeev R. ; Mitter, Sanjoy K. ; Tsitsiklis, John N. ; Zeitouni, Ofer

Author_Institution

MIT, Cambridge, MA, USA

Volume

15

Issue

9

fYear

1993

fDate

9/1/1993 12:00:00 AM

Firstpage

933

Lastpage

942

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

Keywords

geometry; learning systems; signal processing; stochastic processes; PAC learning; curve reconstruction; generalized samples; geometric reconstruction; probably approximately correct learning; sample size bounds; signal processing; stochastic geometry; Bridges; Helium; Information geometry; Laboratories; Machine learning; Probability; Signal processing; Solid modeling; Statistics; Stochastic processes;

fLanguage

English

Journal_Title

Pattern Analysis and Machine Intelligence, IEEE Transactions on

Publisher

ieee

ISSN

0162-8828

Type

jour

DOI

10.1109/34.232080

Filename

232080