Unsupervised Learning for Signal Versus Noise

A. F.M. Smith; Udi E. Makov

doi:10.1109/TIT.1981.1056376

Unsupervised Learning for Signal Versus Noise

Research output: Contribution to journal › Article › peer-review

Abstract

The Bayes solution to the unsupervised sequential learning problem induced by a mixture model for the two-class signal versus noise decision problem generates a computational and storage explosion. A quasi-Bayes approximate learning procedure is proposed that avoids the computational explosion while retaining the flavor of the Bayes solution. Convergence is established and efficiency is investigated.

Original language	English
Pages (from-to)	498-500
Number of pages	3
Journal	IEEE Transactions on Information Theory
Volume	27
Issue number	4
DOIs	https://doi.org/10.1109/TIT.1981.1056376
State	Published - Jul 1981
Externally published	Yes

ASJC Scopus subject areas

Information Systems
Computer Science Applications
Library and Information Sciences

Access to Document

10.1109/TIT.1981.1056376

Cite this

@article{d44b59547b0e4a6dba620f27c2b03f6a,

title = "Unsupervised Learning for Signal Versus Noise",

abstract = "The Bayes solution to the unsupervised sequential learning problem induced by a mixture model for the two-class signal versus noise decision problem generates a computational and storage explosion. A quasi-Bayes approximate learning procedure is proposed that avoids the computational explosion while retaining the flavor of the Bayes solution. Convergence is established and efficiency is investigated.",

author = "Smith, {A. F.M.} and Makov, {Udi E.}",

year = "1981",

month = jul,

doi = "10.1109/TIT.1981.1056376",

language = "English",

volume = "27",

pages = "498--500",

journal = "IEEE Transactions on Information Theory",

issn = "0018-9448",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

number = "4",

}

TY - JOUR

T1 - Unsupervised Learning for Signal Versus Noise

AU - Smith, A. F.M.

AU - Makov, Udi E.

PY - 1981/7

Y1 - 1981/7

N2 - The Bayes solution to the unsupervised sequential learning problem induced by a mixture model for the two-class signal versus noise decision problem generates a computational and storage explosion. A quasi-Bayes approximate learning procedure is proposed that avoids the computational explosion while retaining the flavor of the Bayes solution. Convergence is established and efficiency is investigated.

AB - The Bayes solution to the unsupervised sequential learning problem induced by a mixture model for the two-class signal versus noise decision problem generates a computational and storage explosion. A quasi-Bayes approximate learning procedure is proposed that avoids the computational explosion while retaining the flavor of the Bayes solution. Convergence is established and efficiency is investigated.

UR - http://www.scopus.com/inward/record.url?scp=0019590748&partnerID=8YFLogxK

U2 - 10.1109/TIT.1981.1056376

DO - 10.1109/TIT.1981.1056376

M3 - Article

AN - SCOPUS:0019590748

SN - 0018-9448

VL - 27

SP - 498

EP - 500

JO - IEEE Transactions on Information Theory

JF - IEEE Transactions on Information Theory

IS - 4

ER -

Unsupervised Learning for Signal Versus Noise

Abstract

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this