Application of an Improved Genetic Algorithm to the Learning of Neural Networks

スポンサーリンク

概要

• 論文の詳細を見る

• Recently, the back propagation method, which is one of the algorithms for learning neural networks, has been widely applied to various fields because of its excellent characteristics. But it has drawbacks, for example, slowness of learning speed, the possibility of falling into a local minimum and the necessity of adjusting a learning constant in every application. In this article we propose an algorithm which overcomes some of the drawbacks of the back propagation by using an improved genetic algorithm.

• 社団法人電子情報通信学会の論文
• 1994-04-25

著者

• HIRATA Masaya

  Osaka Prefectural College of Technology

• Inagaki Yoshio

  College Of Engineering University Of Osaka Prefecture

• Kawabata H

  Okayama Prefectural Univ. Soja‐shi Jpn

• Ikuno Yasumasa

  College of Engineering, University of Osaka Prefecture

• Kawabata Hiroaki

  College of Engineering, University of Osaka Prefecture

• Shirao Yoshiaki

  College of Engineering, University of Osaka Prefecture

• Nagahara Toshikuni

  College of Engineering, University of Osaka Prefecture

• Inagaki Yashio

  College of Engineering, University of Osaka Prefecture

• Shirao Yoshiaki

  College Of Engineering University Of Osaka Prefecture

• Ikuno Yasumasa

  College Of Engineering University Of Osaka Prefecture

• Nagahara Toshikuni

  College Of Engineering University Of Osaka Prefecture

関連論文

• Affect of Voltage Sags on Electro-magnetic Contactor : A New Parameter for Sag Characteristics
• Control of Chua's Circuit by Switching a Resistor
• Controlling Chaos in the Maxwell-Bloch Equations with Time Delay (Special Section of Letters Selected from the 1993 IEICE Spring Conference)
• Quasi-Periodicity Route to Chaos in Josephson Transmission Line
• Intermittency of Recurrent Neuron and Its Network Dynamics : Secial Section on Neural Nets, Chaos and Numerics
• Application of an Improved Genetic Algorithm to the Learning of Neural Networks

スポンサーリンク