A Dynamic Node Decaying Method for Pruning Artificial Neural Networks

スポンサーリンク

概要

• 論文の詳細を見る

• This paper presents a dynamic node decaying method (DNDM) for layered artificial neural networks that is suitable for classification problems. Our purpose is not to minimize the total output error but to obtain high generalization ability with minimal structure. Users of the conventional back propagation (BP) learning algorithm can convert their program to the DNDM by simply inserting a few lines. This method is an extension of a previously proposed method to more general classification problems, and its validity is tested with recent standard benchmark problems. In addition, we analyzed the training process and the effects of various parameters. In the method, nodes in a layer compete for survival in an automatic process that uses a criterion. Relatively less important nodes are decayed gradually during BP learning while more important ones play larger roles until the best performance under given conditions is achieved. The criterion evaluates each node by its total influence on progress toward the upper layer, and it is used as the index for dynamic competitive decaying. Two additional criteria are used : Generalization Loss to measure over-fitting and Learning Progress to stop training. Determination of these criteria requires a few human interventions. We have applied this algorithm to several standard benchmark problems such as cancer, diabetes, heart disease, glass, and iris problems. The results show the effectiveness of the method. The classification error and size of the generated networks are comparable to those obtained by other methods that generally require larger modification, or complete rewriting, of the program from the conventional BP algorithm.

• 一般社団法人電子情報通信学会の論文
• 2003-04-01

著者

• Shahjahan Md.

  Department Of Human And Artificial Intelligence Systems Fukui University

• Murase Kazuyuki

  Department Of Human And Artificial Intelligence Systems Fukui University

• Murase Kazuyuki

  Department Of Electronicengineering Faculty Of Engineering Himeji Institute Of Technology

関連論文

• A GA-Based Evolutionary System for Evolving Artificial Neural Networks with Connectionist Learning
• Incremental Evolution with Learning to Develop the Control System of Autonomous Robots for Complex Task
• Quasi-Steady Filamentary Plasma at Atmospheric Pressure.
• Neural Network Training Algorithm with Positive Correlation(Biocybernetics, Neurocomputing)
• A Dynamic Node Decaying Method for Pruning Artificial Neural Networks
• Evolution of Cooperative Ensemble Neural Network Controller for Autonomous Mobile Robots

スポンサーリンク