Growing RBF structures using self-organizing maps

Qingyu Xiong*, Kotaro Hirasawa, Jinglu Hu, Junichi Murata

*この研究の対応する著者

研究成果: Paper査読

6 被引用数 (Scopus)

抄録

We present a novel growing RBF network structure using SOM in this paper. It consists of SOM and RBF networks respectively. The SOM performs unsupervised learning and also the weight vectors belonging to its output nodes are transmitted to the hidden nodes in the RBF networks as the centers of RBF activation functions, as a result one to one correspondence relationship is realized between the output nodes in SOM and the hidden nodes in RBF networks. The RBF networks perform supervised training using delta rule. Therefore, the current output errors in the RBF networks can be used to determine where to insert a new SOM unit according to the rule. This also makes it possible to make the RBF networks grow until a performance criterion is fulfilled or until a desired network size is obtained. The simulations on the two-spirals benchmark are shown to prove the proposed networks have good performance.

本文言語English
ページ107-111
ページ数5
出版ステータスPublished - 2000 12 1
外部発表はい
イベント9th IEEE International Workshop on Robot and Human Interactive Communication RO-MAN2000 - Osaka, Japan
継続期間: 2000 9 272000 9 29

Conference

Conference9th IEEE International Workshop on Robot and Human Interactive Communication RO-MAN2000
国/地域Japan
CityOsaka
Period00/9/2700/9/29

ASJC Scopus subject areas

  • ハードウェアとアーキテクチャ
  • ソフトウェア

フィンガープリント

「Growing RBF structures using self-organizing maps」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