Learning algorithm for nearest-prototype classifiers

Kiichi Urahama, Takeshi Nagao

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Incremental learning algorithms are presented for Nearest Prototype (NP) classifiers. Fuzzification of the 1-NP and k-NP classification rules provides an explicit analytical expression of the membership of data to categories. This expression enables formulation of the prototype placement problem as mathematical programming which can be solved by using a gradient descent algorithm. In addition to the learning algorithm, analog electronic circuits are configured which implement 1-NP and k-NP classifiers.

Original languageEnglish
Title of host publicationProceedings of the International Joint Conference on Neural Networks
PublisherPubl by IEEE
Pages585-588
Number of pages4
Volume1
ISBN (Print)0780314212, 9780780314214
Publication statusPublished - 1993
Externally publishedYes
EventProceedings of 1993 International Joint Conference on Neural Networks. Part 1 (of 3) - Nagoya, Jpn
Duration: Oct 25 1993Oct 29 1993

Other

OtherProceedings of 1993 International Joint Conference on Neural Networks. Part 1 (of 3)
CityNagoya, Jpn
Period10/25/9310/29/93

Fingerprint

Learning algorithms
Classifiers
Mathematical programming
Networks (circuits)

All Science Journal Classification (ASJC) codes

  • Engineering(all)

Cite this

Urahama, K., & Nagao, T. (1993). Learning algorithm for nearest-prototype classifiers. In Proceedings of the International Joint Conference on Neural Networks (Vol. 1, pp. 585-588). Publ by IEEE.

Learning algorithm for nearest-prototype classifiers. / Urahama, Kiichi; Nagao, Takeshi.

Proceedings of the International Joint Conference on Neural Networks. Vol. 1 Publ by IEEE, 1993. p. 585-588.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Urahama, K & Nagao, T 1993, Learning algorithm for nearest-prototype classifiers. in Proceedings of the International Joint Conference on Neural Networks. vol. 1, Publ by IEEE, pp. 585-588, Proceedings of 1993 International Joint Conference on Neural Networks. Part 1 (of 3), Nagoya, Jpn, 10/25/93.
Urahama K, Nagao T. Learning algorithm for nearest-prototype classifiers. In Proceedings of the International Joint Conference on Neural Networks. Vol. 1. Publ by IEEE. 1993. p. 585-588
Urahama, Kiichi ; Nagao, Takeshi. / Learning algorithm for nearest-prototype classifiers. Proceedings of the International Joint Conference on Neural Networks. Vol. 1 Publ by IEEE, 1993. pp. 585-588
@inproceedings{fa6699805b0c4263b33c3921acc67f93,
title = "Learning algorithm for nearest-prototype classifiers",
abstract = "Incremental learning algorithms are presented for Nearest Prototype (NP) classifiers. Fuzzification of the 1-NP and k-NP classification rules provides an explicit analytical expression of the membership of data to categories. This expression enables formulation of the prototype placement problem as mathematical programming which can be solved by using a gradient descent algorithm. In addition to the learning algorithm, analog electronic circuits are configured which implement 1-NP and k-NP classifiers.",
author = "Kiichi Urahama and Takeshi Nagao",
year = "1993",
language = "English",
isbn = "0780314212",
volume = "1",
pages = "585--588",
booktitle = "Proceedings of the International Joint Conference on Neural Networks",
publisher = "Publ by IEEE",

}

TY - GEN

T1 - Learning algorithm for nearest-prototype classifiers

AU - Urahama, Kiichi

AU - Nagao, Takeshi

PY - 1993

Y1 - 1993

N2 - Incremental learning algorithms are presented for Nearest Prototype (NP) classifiers. Fuzzification of the 1-NP and k-NP classification rules provides an explicit analytical expression of the membership of data to categories. This expression enables formulation of the prototype placement problem as mathematical programming which can be solved by using a gradient descent algorithm. In addition to the learning algorithm, analog electronic circuits are configured which implement 1-NP and k-NP classifiers.

AB - Incremental learning algorithms are presented for Nearest Prototype (NP) classifiers. Fuzzification of the 1-NP and k-NP classification rules provides an explicit analytical expression of the membership of data to categories. This expression enables formulation of the prototype placement problem as mathematical programming which can be solved by using a gradient descent algorithm. In addition to the learning algorithm, analog electronic circuits are configured which implement 1-NP and k-NP classifiers.

UR - http://www.scopus.com/inward/record.url?scp=0027855188&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0027855188&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:0027855188

SN - 0780314212

SN - 9780780314214

VL - 1

SP - 585

EP - 588

BT - Proceedings of the International Joint Conference on Neural Networks

PB - Publ by IEEE

ER -