標題: Improved MS_CMAC neural networks by integrating a simplified UFN model
作者: Jan, Jiun-Chi
Hung, Shih-Lin
土木工程學系
Department of Civil Engineering
關鍵字: virtual grid-distributed data points;a tree structure network;UFN
公開日期: 1-Apr-2008
摘要: Macro_Structure_CMAC (MS_CMAC) is a variational CMAC neural network that is designed for modeling smooth functional mappings. The MS_CMAC learning strategy involves constructing virtual grid-distributed data points from random-distributed training data points, and then using the virtual data points to train a tree structure network that is composed of one-dimensional CMAC nodes. A disadvantage of the MS_CMAC is that the prediction errors near the boundary area might sometimes be unexpectedly large. Another disadvantage of the MS_CMAC is that generating virtual grid-distributed data points generally takes a long computational time. Therefore, this study develops an improved model by integrating an unsupervised fuzzy neural network (UFN) into the MS_CMAC to initialize systematically the virtual grid-distributed data points. Additionally, a new error feedback ratio function is adopted to speed up the MS_CMAC training. Several numerical problems are considered to test the improved MS_CMAC. The computed results indicate that a simplified UFN model can produce good initial values of the virtual grid-distributed data points to aggrandize MS_CMAC training. The MS_CMAC prediction is also improved by using the initialized virtual grid-distributed data points.
URI: http://dx.doi.org/10.1007/s11063-007-9067-4
http://hdl.handle.net/11536/9537
ISSN: 1370-4621
DOI: 10.1007/s11063-007-9067-4
期刊: NEURAL PROCESSING LETTERS
Volume: 27
Issue: 2
起始頁: 163
結束頁: 177
Appears in Collections:Articles


Files in This Item:

  1. 000253529100006.pdf