F-007 An Efficient Construction of RBF Network Based on Training by SOM

スポンサーリンク

概要

• 論文の詳細を見る

• In this work we proposed to train both input to hidden as well as hidden to output layer weights of a RBF network using Self-Organizing Maps (SOM) training. Initially a two dimensional SOM is trained. Once SOM training is over, the SOM input to output weights determine the RBF hidden units' location in problem feature space. Next, for every individual sample the winner SOM output is identified, and the label (class) of the sample is tagged with SOM outputs. This tag information is used to decide the connection weights between RBF middle layer nodes to output nodes. Thus by just executing SOM the RBF network is constructed. The performance is compared with multilayer Perceptron trained with error back propagation.

• FIT(電子情報通信学会・情報処理学会)推進委員会の論文
• 2008-08-20

著者

• 山下 和彦

  岩手県立大学ソフトウェア情報学部

• 水野 佑治

  岩手県大

• 山下 和彦

  岩手県大

• Chakraborty Goutam

  岩手県大

関連論文

• 6Q-6 自己組織化マップを用いた動径基底関数ネットワークの構築(ニューラルネット(2),学生セッション,人工知能と認知科学)
• F-029 自己組織化マップを用いた動径基底関数ネットワークの性能評価(F分野:人工知能・ゲーム,一般論文)
• F-008 An Novel Soft Margin Classifier Using Genetic Algorithm
• F-007 An Efficient Construction of RBF Network Based on Training by SOM
• G-010 遺伝子発現データを用いた病理診断における遺伝子選択手法の提案(生体情報科学,一般論文)
• H_027 A Health Life-style Checke List and Analysis

スポンサーリンク