Learning algorithm for nearest-prototype classifiers

Kiichi Urahama, Takeshi Nagao

研究成果: Chapter in Book/Report/Conference proceedingConference contribution

抄録

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.

本文言語英語
ホスト出版物のタイトルProceedings of the International Joint Conference on Neural Networks
出版社Publ by IEEE
ページ585-588
ページ数4
1
ISBN(印刷版)0780314212, 9780780314214
出版ステータス出版済み - 1993
外部発表はい
イベントProceedings of 1993 International Joint Conference on Neural Networks. Part 1 (of 3) - Nagoya, Jpn
継続期間: 10 25 199310 29 1993

その他

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

All Science Journal Classification (ASJC) codes

  • 工学(全般)

フィンガープリント

「Learning algorithm for nearest-prototype classifiers」の研究トピックを掘り下げます。これらがまとまってユニークなフィンガープリントを構成します。

引用スタイル