LINEAR DECISION FUNCTIONS FOR PATTERN CLASSIFICATION

Sik-Sang Yau, TT LIN TT

Research output: Chapter in Book/Report/Conference proceedingChapter

Abstract

Linear decision functions approximating the optimal decision functions in the least-mean-square-error sense are determined. By choosing a particular form of optimal decision functions, it is possible to evaluate the linear decision functions explicitly. It is found that this approach embodies some existing methods for evaluating linear discriminant functions, and is applicable to more general performance criteria. An iterative algorithm which improves the performance of the linear classifier based on linear decision functions substantially is proposed.

Original languageEnglish (US)
Title of host publicationUnknown Host Publication Title
Pages448-452
Number of pages5
StatePublished - 1968
Externally publishedYes
EventPrinceton Univ-2nd Annual Princeton Conference on Information Sciences & Systems-Proc -
Duration: Mar 25 1968Mar 26 1968

Other

OtherPrinceton Univ-2nd Annual Princeton Conference on Information Sciences & Systems-Proc
Period3/25/683/26/68

Fingerprint

Pattern recognition
Mean square error
Classifiers

ASJC Scopus subject areas

  • Engineering(all)

Cite this

Yau, S-S., & LIN TT, TT. (1968). LINEAR DECISION FUNCTIONS FOR PATTERN CLASSIFICATION. In Unknown Host Publication Title (pp. 448-452)

LINEAR DECISION FUNCTIONS FOR PATTERN CLASSIFICATION. / Yau, Sik-Sang; LIN TT, TT.

Unknown Host Publication Title. 1968. p. 448-452.

Research output: Chapter in Book/Report/Conference proceedingChapter

Yau, S-S & LIN TT, TT 1968, LINEAR DECISION FUNCTIONS FOR PATTERN CLASSIFICATION. in Unknown Host Publication Title. pp. 448-452, Princeton Univ-2nd Annual Princeton Conference on Information Sciences & Systems-Proc, 3/25/68.
Yau S-S, LIN TT TT. LINEAR DECISION FUNCTIONS FOR PATTERN CLASSIFICATION. In Unknown Host Publication Title. 1968. p. 448-452
Yau, Sik-Sang ; LIN TT, TT. / LINEAR DECISION FUNCTIONS FOR PATTERN CLASSIFICATION. Unknown Host Publication Title. 1968. pp. 448-452
@inbook{7a4e2667a88640d4abb86cb667054ea4,
title = "LINEAR DECISION FUNCTIONS FOR PATTERN CLASSIFICATION",
abstract = "Linear decision functions approximating the optimal decision functions in the least-mean-square-error sense are determined. By choosing a particular form of optimal decision functions, it is possible to evaluate the linear decision functions explicitly. It is found that this approach embodies some existing methods for evaluating linear discriminant functions, and is applicable to more general performance criteria. An iterative algorithm which improves the performance of the linear classifier based on linear decision functions substantially is proposed.",
author = "Sik-Sang Yau and {LIN TT}, TT",
year = "1968",
language = "English (US)",
pages = "448--452",
booktitle = "Unknown Host Publication Title",

}

TY - CHAP

T1 - LINEAR DECISION FUNCTIONS FOR PATTERN CLASSIFICATION

AU - Yau, Sik-Sang

AU - LIN TT, TT

PY - 1968

Y1 - 1968

N2 - Linear decision functions approximating the optimal decision functions in the least-mean-square-error sense are determined. By choosing a particular form of optimal decision functions, it is possible to evaluate the linear decision functions explicitly. It is found that this approach embodies some existing methods for evaluating linear discriminant functions, and is applicable to more general performance criteria. An iterative algorithm which improves the performance of the linear classifier based on linear decision functions substantially is proposed.

AB - Linear decision functions approximating the optimal decision functions in the least-mean-square-error sense are determined. By choosing a particular form of optimal decision functions, it is possible to evaluate the linear decision functions explicitly. It is found that this approach embodies some existing methods for evaluating linear discriminant functions, and is applicable to more general performance criteria. An iterative algorithm which improves the performance of the linear classifier based on linear decision functions substantially is proposed.

UR - http://www.scopus.com/inward/record.url?scp=0014372203&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0014372203&partnerID=8YFLogxK

M3 - Chapter

AN - SCOPUS:0014372203

SP - 448

EP - 452

BT - Unknown Host Publication Title

ER -