A Comparative Study of Eight Learning Algorithms for Artifical Neural Networks Based on a Real Application

スポンサーリンク

概要

• 論文の詳細を見る

• The aim of this study is to offer additional experimental evaluation on learning algorithms for artificial neural networks by testing and comparing the normalized backpropagation algorithm (NBP), previously proposed by the authors, and six other alternatives based on a particular application to financial forecasting. The algorithms are the original backpropagation (OBP), the NBP, backpropagation with momentum (two versions), the delta-bar-delta, the superSAB, the rprop and the quickprop algorithm.

• 社団法人電子情報通信学会の論文
• 1998-02-25

著者

• Ikeda H

  Department Of Electrical Electronic And Communication Engineering Chuo University

• SOLANO Yadira

  the Faculty of Engineering, Dept. of Computer Sciences, University of Costa Rica

• IKEDA Hiroaki

  the Faculty of Engineering, Dept. of Electric and Electronics Engineering, Chiba University

• Solano Y

  The Faculty Of Engineering Dept. Of Computer Sciences University Of Costa Rica:(present Address)the

関連論文

• CMOS Zero-Temperature-Coefficient Point Voltage Reference with Variable-Output-Voltage Level(Analog Circuit Techniques and Related Topics)
• Drain Current Zero-Temperature-Coefficient Point for CMOS Temperature-Voltage Converter Operating in Strong Inversion(Analog Circuit Techniques and Related Topics)
• A Comparative Study of Eight Learning Algorithms for Artifical Neural Networks Based on a Real Application

スポンサーリンク