A Probabilistic Iterative Architecture for Classification

M. B. Clausing; Thomas Sudkamp

doi:10.1109/NAECON.1990.112934

A Probabilistic Iterative Architecture for Classification

M. B. Clausing, Thomas Sudkamp

Computer Science and Engineering

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

A classification architecture that uses probabilistic representation of support and conditionalization and expectation for updating belief is presented. The updating is guided by a utility function that determines the type of information to be acquired. Expected entropy is used as the utility measure. The three major components of a classification system are the representation of the domain information, the evidence, and the support updating paradigm. The representative of domain knowledge and evidence is described. A general overview of the classification architecture is given. The computations and assumptions required in this iterative method are presented. A detailed example illustrating the generation of support based on the acquisition of one item of evidence is given.

Original language	English
Title of host publication	IEEE Conference on Aerospace and Electronics
Pages	1171-1176
Number of pages	6
DOIs	https://doi.org/10.1109/NAECON.1990.112934
State	Published - 1990
Event	1990 IEEE National Aerospace and Electronics Conference - Dayton, OH, USA Duration: May 21 1990 → May 25 1990

Conference

Conference	1990 IEEE National Aerospace and Electronics Conference
Abbreviated title	NAECON 1990
City	Dayton, OH, USA
Period	5/21/90 → 5/25/90

ASJC Scopus Subject Areas

General Engineering

Keywords

Application software
Artificial intelligence
Calculus
Character generation
Computer architecture
Computer science
Entropy
Joining processes
Probability, Logic

Disciplines

Computer Sciences
Engineering
Mathematics
Physical Sciences and Mathematics

Access to Document

10.1109/NAECON.1990.112934License: Unspecified

Cite this

@inproceedings{4f9d4d21b5eb4faf8ec3562d44f0b553,

title = "A Probabilistic Iterative Architecture for Classification",

abstract = " A classification architecture that uses probabilistic representation of support and conditionalization and expectation for updating belief is presented. The updating is guided by a utility function that determines the type of information to be acquired. Expected entropy is used as the utility measure. The three major components of a classification system are the representation of the domain information, the evidence, and the support updating paradigm. The representative of domain knowledge and evidence is described. A general overview of the classification architecture is given. The computations and assumptions required in this iterative method are presented. A detailed example illustrating the generation of support based on the acquisition of one item of evidence is given.",

keywords = "Application software, Artificial intelligence, Calculus, Character generation, Computer architecture, Computer science, Entropy, Joining processes, Probability, Logic",

author = "Clausing, {M. B.} and Thomas Sudkamp",

year = "1990",

doi = "10.1109/NAECON.1990.112934",

language = "English",

pages = "1171--1176",

booktitle = "IEEE Conference on Aerospace and Electronics",

note = "1990 IEEE National Aerospace and Electronics Conference ; Conference date: 21-05-1990 Through 25-05-1990",

}

TY - GEN

T1 - A Probabilistic Iterative Architecture for Classification

AU - Clausing, M. B.

AU - Sudkamp, Thomas

PY - 1990

Y1 - 1990

N2 - A classification architecture that uses probabilistic representation of support and conditionalization and expectation for updating belief is presented. The updating is guided by a utility function that determines the type of information to be acquired. Expected entropy is used as the utility measure. The three major components of a classification system are the representation of the domain information, the evidence, and the support updating paradigm. The representative of domain knowledge and evidence is described. A general overview of the classification architecture is given. The computations and assumptions required in this iterative method are presented. A detailed example illustrating the generation of support based on the acquisition of one item of evidence is given.

AB - A classification architecture that uses probabilistic representation of support and conditionalization and expectation for updating belief is presented. The updating is guided by a utility function that determines the type of information to be acquired. Expected entropy is used as the utility measure. The three major components of a classification system are the representation of the domain information, the evidence, and the support updating paradigm. The representative of domain knowledge and evidence is described. A general overview of the classification architecture is given. The computations and assumptions required in this iterative method are presented. A detailed example illustrating the generation of support based on the acquisition of one item of evidence is given.

KW - Application software

KW - Artificial intelligence

KW - Calculus

KW - Character generation

KW - Computer architecture

KW - Computer science

KW - Entropy

KW - Joining processes

KW - Probability, Logic

UR - http://www.scopus.com/inward/record.url?scp=0025657399&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0025657399&partnerID=8YFLogxK

UR - https://corescholar.libraries.wright.edu/cse/463

U2 - 10.1109/NAECON.1990.112934

DO - 10.1109/NAECON.1990.112934

M3 - Conference contribution

SP - 1171

EP - 1176

BT - IEEE Conference on Aerospace and Electronics

T2 - 1990 IEEE National Aerospace and Electronics Conference

Y2 - 21 May 1990 through 25 May 1990

ER -

A Probabilistic Iterative Architecture for Classification

Abstract

Conference

ASJC Scopus Subject Areas

Keywords

Disciplines

Access to Document

Other files and links

Cite this