Universal Learning Theory

Marcus Hutter

doi:10.1007/978-0-387-30164-8_861

Universal Learning Theory

Marcus Hutter

Research output: Chapter in Book/Report/Conference proceeding › Entry for encyclopedia/dictionary › peer-review

Abstract

Universal (machine) learning is concerned with the development and study of algorithms that are able to learn from data in a very large range of environments with as few assumptions as possible. The class of environments typically considered includes all computable stochastic processes.

Original language	English
Title of host publication	Encyclopedia of Machine Learning
Editors	Claude Sammut & Geoffrey I.Webb
Place of Publication	New York
Publisher	Springer
Pages	1001-1008pp
Volume	6
ISBN (Print)	9780387307688
DOIs	https://doi.org/10.1007/978-0-387-30164-8_861
Publication status	Published - 2010

Access to Document

10.1007/978-0-387-30164-8_861

Cite this

@inbook{9378a9a3885543b7b6c90cf84b5e33e3,

title = "Universal Learning Theory",

abstract = "Universal (machine) learning is concerned with the development and study of algorithms that are able to learn from data in a very large range of environments with as few assumptions as possible. The class of environments typically considered includes all computable stochastic processes.",

author = "Marcus Hutter",

year = "2010",

doi = "10.1007/978-0-387-30164-8_861",

language = "English",

isbn = "9780387307688",

volume = "6",

pages = "1001--1008pp",

editor = "{Claude Sammut & Geoffrey I.Webb}",

booktitle = "Encyclopedia of Machine Learning",

publisher = "Springer",

}

TY - CHAP

T1 - Universal Learning Theory

AU - Hutter, Marcus

PY - 2010

Y1 - 2010

N2 - Universal (machine) learning is concerned with the development and study of algorithms that are able to learn from data in a very large range of environments with as few assumptions as possible. The class of environments typically considered includes all computable stochastic processes.

AB - Universal (machine) learning is concerned with the development and study of algorithms that are able to learn from data in a very large range of environments with as few assumptions as possible. The class of environments typically considered includes all computable stochastic processes.

U2 - 10.1007/978-0-387-30164-8_861

DO - 10.1007/978-0-387-30164-8_861

M3 - Entry for encyclopedia/dictionary

SN - 9780387307688

VL - 6

SP - 1001

EP - 1008

BT - Encyclopedia of Machine Learning

A2 - null, Claude Sammut & Geoffrey I.Webb

PB - Springer

CY - New York

ER -

Universal Learning Theory

Abstract

Access to Document

Fingerprint

Cite this