REPRESENTATIVENESS AND UNCERTAINTY IN CLASSIFICATION SYSTEMS.

Paul R Cohen, Alvah Davis, David Day, Michael Greenberg, Rick Kjeldsen, Susan Lander, Cynthia Loiselle

Research output: Contribution to journalArticle

19 Citations (Scopus)

Abstract

The choice of implication as a representation for empirical associations and for deduction as a mode of inference requires a mechanism extraneous to deduction to manage uncertainty associated with inference. Consequently, the interpretation of representations of uncertainty is unclear. Representativeness, of degree of fit, is proposed as an interpretation of degree of belief for classification tasks. The calculation of representativeness depends on the nature of the associations between evidence and conclusions. Patterns of associations are characterized as endorsements of conclusions. We discuss an expert system that uses endorsements to control the search for the most representative conclusion, given evidence. Some approaches from the biomedical field are examined.

Original languageEnglish (US)
Pages (from-to)136-149
Number of pages14
JournalAI Magazine
Volume6
Issue number3
StatePublished - Sep 1985
Externally publishedYes

Fingerprint

Expert systems
Uncertainty

ASJC Scopus subject areas

  • Artificial Intelligence
  • Control and Systems Engineering

Cite this

Cohen, P. R., Davis, A., Day, D., Greenberg, M., Kjeldsen, R., Lander, S., & Loiselle, C. (1985). REPRESENTATIVENESS AND UNCERTAINTY IN CLASSIFICATION SYSTEMS. AI Magazine, 6(3), 136-149.

REPRESENTATIVENESS AND UNCERTAINTY IN CLASSIFICATION SYSTEMS. / Cohen, Paul R; Davis, Alvah; Day, David; Greenberg, Michael; Kjeldsen, Rick; Lander, Susan; Loiselle, Cynthia.

In: AI Magazine, Vol. 6, No. 3, 09.1985, p. 136-149.

Research output: Contribution to journalArticle

Cohen, PR, Davis, A, Day, D, Greenberg, M, Kjeldsen, R, Lander, S & Loiselle, C 1985, 'REPRESENTATIVENESS AND UNCERTAINTY IN CLASSIFICATION SYSTEMS.', AI Magazine, vol. 6, no. 3, pp. 136-149.
Cohen PR, Davis A, Day D, Greenberg M, Kjeldsen R, Lander S et al. REPRESENTATIVENESS AND UNCERTAINTY IN CLASSIFICATION SYSTEMS. AI Magazine. 1985 Sep;6(3):136-149.
Cohen, Paul R ; Davis, Alvah ; Day, David ; Greenberg, Michael ; Kjeldsen, Rick ; Lander, Susan ; Loiselle, Cynthia. / REPRESENTATIVENESS AND UNCERTAINTY IN CLASSIFICATION SYSTEMS. In: AI Magazine. 1985 ; Vol. 6, No. 3. pp. 136-149.
@article{5625e0a74ec744968cd9edc5da466904,
title = "REPRESENTATIVENESS AND UNCERTAINTY IN CLASSIFICATION SYSTEMS.",
abstract = "The choice of implication as a representation for empirical associations and for deduction as a mode of inference requires a mechanism extraneous to deduction to manage uncertainty associated with inference. Consequently, the interpretation of representations of uncertainty is unclear. Representativeness, of degree of fit, is proposed as an interpretation of degree of belief for classification tasks. The calculation of representativeness depends on the nature of the associations between evidence and conclusions. Patterns of associations are characterized as endorsements of conclusions. We discuss an expert system that uses endorsements to control the search for the most representative conclusion, given evidence. Some approaches from the biomedical field are examined.",
author = "Cohen, {Paul R} and Alvah Davis and David Day and Michael Greenberg and Rick Kjeldsen and Susan Lander and Cynthia Loiselle",
year = "1985",
month = "9",
language = "English (US)",
volume = "6",
pages = "136--149",
journal = "AI Magazine",
issn = "0738-4602",
publisher = "AI Access Foundation",
number = "3",

}

TY - JOUR

T1 - REPRESENTATIVENESS AND UNCERTAINTY IN CLASSIFICATION SYSTEMS.

AU - Cohen, Paul R

AU - Davis, Alvah

AU - Day, David

AU - Greenberg, Michael

AU - Kjeldsen, Rick

AU - Lander, Susan

AU - Loiselle, Cynthia

PY - 1985/9

Y1 - 1985/9

N2 - The choice of implication as a representation for empirical associations and for deduction as a mode of inference requires a mechanism extraneous to deduction to manage uncertainty associated with inference. Consequently, the interpretation of representations of uncertainty is unclear. Representativeness, of degree of fit, is proposed as an interpretation of degree of belief for classification tasks. The calculation of representativeness depends on the nature of the associations between evidence and conclusions. Patterns of associations are characterized as endorsements of conclusions. We discuss an expert system that uses endorsements to control the search for the most representative conclusion, given evidence. Some approaches from the biomedical field are examined.

AB - The choice of implication as a representation for empirical associations and for deduction as a mode of inference requires a mechanism extraneous to deduction to manage uncertainty associated with inference. Consequently, the interpretation of representations of uncertainty is unclear. Representativeness, of degree of fit, is proposed as an interpretation of degree of belief for classification tasks. The calculation of representativeness depends on the nature of the associations between evidence and conclusions. Patterns of associations are characterized as endorsements of conclusions. We discuss an expert system that uses endorsements to control the search for the most representative conclusion, given evidence. Some approaches from the biomedical field are examined.

UR - http://www.scopus.com/inward/record.url?scp=0022118435&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0022118435&partnerID=8YFLogxK

M3 - Article

AN - SCOPUS:0022118435

VL - 6

SP - 136

EP - 149

JO - AI Magazine

JF - AI Magazine

SN - 0738-4602

IS - 3

ER -