An Analog Neural Network System with Learning Capability Using Simultaneous Perturbation

スポンサーリンク

概要

• 論文の詳細を見る

• In this paper, we describe an implementation of analog neural network system with on-line learning capability. A learning rule using the simultaneous perturbation is adopted. Compared with usage of the ordinary back-propagation method, we can easily implement the simultaneous perturbation learning rule. The neural system can monitor weight values and an error value. The exclusive OR problem and a simple function problem are shown.

• 社団法人電子情報通信学会の論文
• 1999-12-25

著者

• Maeda Yutaka

  Faculty Of Engineering Kansai University

• KUSUHASHI Toshiyuki

  Faculty of Engineering, Kansai University

• Kusuhashi Toshiyuki

  Faculty Of Engineering Kansai University

関連論文

• An Analog Neural Network System with Learning Capability Using Simultaneous Perturbation
• A Separation of Electroretinograms for Diabetic Retinopathy

スポンサーリンク