標題: Optimum design for artificial neural networks: an example in a bicycle derailleur system
作者: Lin, TY
Tseng, CH
機械工程學系
Department of Mechanical Engineering
關鍵字: neural networks;optimization;Taguchi method;design of experiments;bicycle derailleur systems
公開日期: 1-Feb-2000
摘要: The integration of neural networks and optimization provides a tool for designing network parameters and improving network performance. In this paper, the Taguchi method and the Design of Experiment (DOE) methodology are used to optimize network parameters. The users have to recognize the application problems and choose a suitable Artificial Neural Network model. Optimization problems can then be defined according to the model. The Taguchi method is first applied to a problem to find out the more important factors, then the DOE methodology is used for further analysis and forecasting. A Learning Vector Quantization example is shown for an application to bicycle derailleur systems. (C) 2000 Elsevier Science Ltd. All rights reserved.
URI: http://dx.doi.org/10.1016/S0952-1976(99)00045-7
http://hdl.handle.net/11536/30769
ISSN: 0952-1976
DOI: 10.1016/S0952-1976(99)00045-7
期刊: ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE
Volume: 13
Issue: 1
起始頁: 3
結束頁: 14
Appears in Collections:Articles


Files in This Item:

  1. 000084882300002.pdf