题名

An Electromagnetism Algorithm of Neural Network Analysis-An Application to Textile Retail Operation

并列篇名

模擬電磁神經網路訓練應用於紡織業零售商營運分析

DOI

10.29977/JCIIE.200401.0006

作者

巫沛倉(Peitsang Wu);楊文宏(Wen-Hung Yang);魏乃捷(Nai-Chieh Wei)

关键词

類神經網路 ; 模擬電磁演算法 ; 快速回應 ; 紡織製造模擬 ; 零售商營運 ; neural networks ; electromagnetism algorithms ; quick response ; textile manaufacturing ; retail operations

期刊名称

工業工程學刊

卷期/出版年月

21卷1期(2004 / 01 / 01)

页次

59 - 67

内容语文

英文

中文摘要

本研究應用一個新的啓發式演算法-『模擬電磁演算法』於類神經網路訓練,並利用此類神經網路來分析零售商營運模式中模擬系統的主要輸入參數與輸出成效的關係。模擬電磁神經網路應用電磁理論中電荷同性相斥與異性相吸的原理,來修正神經網路連結權重値,使其收斂至最佳權重值,而不會落入區域最佳解。研究結果顯示,模擬電磁演算法收斂的速度比遺傳演算法及倒傳遞演算法更爲快速且更省記憶體空間。

英文摘要

This paper applies a heuristic algorithm, called the ”Electromagnetism Algorithm” (EM) [3], for neural network training. We develop a meta-model of the relationships between key inputs and performance measures of an apparel retail operations using neural network technology. This method simulates the electromagnetism theory of physics by considering each weight connection in a neural network as an electrical charge. Through the attraction and repulsion of the charges, weights move toward the optimality without being trapped into local optima like other algorithms such as genetic algorithm and gradient descent method. The computation results show that the EM algorithm not only converges much faster than those of genetic algorithms and back propagation algorithms in terms of CPU time but also saves more memories than those in genetic algorithms and back propagation algorithms.

主题分类 工程學 > 工程學總論
参考文献
  1. Alpaydin, G.,G. Dundar,S. Balkir(2002).Evolution-based design of fuzzy networks using self-adapting genetic parameters.IEEE Transactions on Fuzzy Systems,10(2),211-221.
  2. Auer, P.,N. C. Bianchi(2002).Adaptive and self-confident on-line learning algorithm.Journal of Computer and System Sciences,10,48-752.
  3. Birbil, S. I.,S. C. Fang(2003).Electromagnetism-like mechanism for global optimization.Journal of Global Optimization,25,263-282.
  4. Chang, W. F.,M. W. Mark(1999).A conjugate gradient learning algorithm for recurrent neural networks.Neurocompution,24,73-189.
  5. Cordon, O.,F. Herrera,P. Villar(2001).Generating the knowledge base of a fuzzy rule-based system by the genetic learning of the data base.IEEE Transactions on Fuzzy Systems,9(4),667-674.
  6. Devert, W.,M. R. Mateen,A. T. Louis(2002).E-net: evolutionary neural network synthesis.Neurocomputing,42,171-196.
  7. Hunter, N. A.(1990).The Textile Institute, Manchester, MA, U. S. A..
  8. Hunter, N. A.,R. E. King,H. L W. Nuttle(1992).An apparel-supply system for QR retailing.Journal of the Textiles Institute,83(3),462-471.
  9. Hunter, N. A.,R. E. King,H. L W. Nuttle(1991).Comparison of quick response and traditional retailing performance through stochastic simulation modeling.NCSU-IE Technical Report, No.91-6, Department of Industrial Engineering, North Carolina State University.
  10. Hunter, N. A.,R. E. King,H. L W. Nuttle,J. R. Wilson(1993).North Carolina apparel pipeline modeling project.International Journal of Clothing Science and Technology,5(3/4),19-24.
  11. Jang, G. S.(1993).Intelligent stock trading system with price trend prediction and reversal recognition using dual-module neural networks.Journal of Applied Intelligence,3,225-248.
  12. Kramer, H.,V. Sangiovanni(1989).Efficient parallel learning algorithm for neural networks.advances in neural information processing systems,1,40-48.
  13. Mandischer, M.(2002).A comparison of evolution strategies and backpropagation for neural network training.Neurocomputing,42,87-117.
  14. Nuttle, H. L. W.,R. E. King,N. A. Hunter(1991).A stochastic model of the apparel-retailing process for seasonal apparel.Journal of the Textiles Institute,82(2),247-256.
  15. Schmidhuber, J.,S. Hochreiter(1996).Guessing can outperform many long time lag algorithms.Technical Note, IDSIA.
  16. Wu, P.(1997).Neural networks and fuzzy control with application manufacturing and management.Ph.D. dissertation, North Carolina State University.
  17. Wu, P.,S. C. Fang,H. L. W. Nuttle(2002).Efficient neural network learning using second order information with fuzzy control.Neurocomputing,43(1~4),197-217.
  18. Wu, P.,S. C. Fang,H. L. W. Nuttle,R. E. King(1995).Decision surface modeling of apparel retail operations using neural network technology.International Journal of Operation & Quantitative Management,1(1),33-47.
  19. Yang, W. H.(2002).A Study on the intelligent neural network training using the electromagnetism algorithm.Master thesis, Department of Industrial Engineering and Management, I-Shou University.