Learning from a population of hypotheses

Michael Kearns, H. Sebastian Seung

Research output: Chapter in Book/Report/Conference proceedingConference contribution

8 Scopus citations

Abstract

A population learning model is introduced. In this model a population learner is provided with an oracle that on each call produces a function that is consistent with an independent random sample of the unknown target function. Thus, each call to the hypothesis oracle causes a new sample of m random examples to be drawn, and for a function consistent with these m examples to be returned to the population learner.

Original languageEnglish (US)
Title of host publicationProceedings of the 6th annual conference on Computational learning theory, COLT 1993
PublisherPubl by ACM
Pages101-110
Number of pages10
ISBN (Print)0897916115, 9780897916110
DOIs
StatePublished - 1993
Externally publishedYes
EventProceedings of the 6th Annual ACM Conference on Computational Learning Theory - Santa Cruz, CA, USA
Duration: Jul 26 1993Jul 28 1993

Publication series

NameProceedings of the 6th annual conference on Computational learning theory, COLT 1993

Conference

ConferenceProceedings of the 6th Annual ACM Conference on Computational Learning Theory
CitySanta Cruz, CA, USA
Period7/26/937/28/93

All Science Journal Classification (ASJC) codes

  • General Engineering

Fingerprint

Dive into the research topics of 'Learning from a population of hypotheses'. Together they form a unique fingerprint.

Cite this