RECONSIDERING THE APPLICATION SCOPE OF FUZZY NEURAL NETWORKS

NCUIR > School of Management at National Central University > Department of Business Administration > journal & Dissertation > Item 987654321/51768

Please use this identifier to cite or link to this item: http://ir.lib.ncu.edu.tw/handle/987654321/51768

Title:	RECONSIDERING THE APPLICATION SCOPE OF FUZZY NEURAL NETWORKS
Authors:	Yen,EC
Contributors:	企業管理學系
Date:	2011
Issue Date:	2012-03-27 19:05:09 (UTC+8)
Publisher:	國立中央大學
Abstract:	In this paper, we first examine limitations of fuzzy neural networks. We find the following. (1) If training errors are the main concerns, Spline can perform better than the generalized dynamic fuzzy neural network (GD-FNN). (2) If the model is nonlinear with a disturbance term, the testing error of the GD-FNN is very large. If the model is chaotic with a disturbance term, both the training error and testing error of the GD-FNN are very large. (3) Using a sequential algorithm as in the GD-FNN, we would always be trapped at the local minima rather than the global minimum. In addition, we propose to use the characteristics among moments and fuzzy rules to identify the density function in advance.
Relation:	INTERNATIONAL JOURNAL OF UNCERTAINTY FUZZINESS AND KNOWLEDGE-BASED SYSTEMS
Appears in Collections:	[Department of Business Administration ] journal & Dissertation

Files in This Item:

File	Description	Size	Format
index.html		0Kb	HTML	452	View/Open

社群 sharing