A Structural Learning of Neural-Network Classifiers Using PCA Networks and Species Genetic Algorithms(Special Section of Papers Selected from ITC-CSCC'97)

スポンサーリンク

概要

• 論文の詳細を見る

• We present experimental results for a structural learning method of feed-forward neural-network classifiers using Principal Component Analysis(PCA)network and Species Genetic Algorithm(SGA). PCA network is used as a means for reducing the number of input units. SGA, a modified GA, is employed for selecting the proper number of hidden units and optimizing the connection links. Experimental results show that the procesed method is a useful tool for choosing an approariate architecture for high dimensions.

• 社団法人電子情報通信学会の論文
• 1998-06-25

著者

• AOKI Yoshinao

  Graduate School of Eng., Hokkaido University

• Aoki Y

  Hokkaido Univ. Jpn

• Kim Sang-woon

  The Department Of Computer Eng. Myongji University

• SHIN Seong-Hyo

  the Department of Computer Eng., Myongji University

• Shin Seong-hyo

  The Department Of Computer Eng. Myongji University

• Aoki Yoshinao

  Graduate School Of Eng. Hokkaido University

関連論文

• Preliminary Study on a Sign-Language Chatting System between Korea and Japan for Avatar Communication on the Internet
• Design of a Sign-Language Keyframe Editor Using Inverse Kinematics
• A-14-17 A Study on Human Communication in Avatar Language Using VR Technology
• A-14-7 Preliminary Experiments on Sign-Language Communication between Korean, Chinese, and Japanese
• A Structural Learning of Neural-Network Classifiers Using PCA Networks and Species Genetic Algorithms(Special Section of Papers Selected from ITC-CSCC'97)

スポンサーリンク