English  |  正體中文  |  简体中文  |  Items with full text/Total items : 26988/38789
Visitors : 2357590      Online Users : 33
RC Version 4.0 © Powered By DSPACE, MIT. Enhanced by NTU Library IR team.
Scope Adv. Search
LoginUploadHelpAboutAdminister

Please use this identifier to cite or link to this item: http://ntour.ntou.edu.tw:8080/ir/handle/987654321/28625

Title: Scale Shrinking Transformation and Applications
Authors: Yu-Chen Chen;Keng-Hsuan Wu;Jyun-Ting Lai;Jung-Hua Wang
Contributors: NTOU:Department of Electrical Engineering
國立臺灣海洋大學:電機工程學系
Keywords: Shrinking Transformation;Feedforward Neural Networks;Scale Divergence;Function Approximation
Shrinking Transformation;Feedforward Neural Networks;Scale Divergence;Function Approximation
Date: 2006-09
Issue Date: 2011-10-21T02:38:35Z
Publisher: 3rd International Conference on Soft Computing and Intelligent Systems and 7th International Symposium on advanced Intelligent Systems (SCIS & ISIS 2006)
Abstract: Abstract:this paper presents a novel information processing technique called scale shrinking transformation (SST). SST comprises three steps: initialization, matrix transformation, and using the column vectors of the transformed matrix as the new input vectors. The essence of SST is that the structural correlation between original inputs can be obtained. More significantly, the transformed matrix contains elements with much smaller scale variation. When applied to existing feedforward neural networks, it can alleviate problems commonly encountered in tasks of function approximation, separating nonlinearly classes, and noise filtering. When the column vectors are used as the new input to a feedforward network that comprises hidden layers, training speed can be reduced. The input scale divergence problem that plagues higher-order neural networks can also be alleviated with SST.
Relation: pp.698-703
URI: http://ntour.ntou.edu.tw/handle/987654321/28625
Appears in Collections:[電機工程學系] 演講及研討會

Files in This Item:

File Description SizeFormat
index.html0KbHTML308View/Open


All items in NTOUR are protected by copyright, with all rights reserved.

 


著作權政策宣告: 本網站之內容為國立臺灣海洋大學所收錄之機構典藏,無償提供學術研究與公眾教育等公益性使用,請合理使用本網站之內容,以尊重著作權人之權益。
網站維護: 海大圖資處 圖書系統組
DSpace Software Copyright © 2002-2004  MIT &  Hewlett-Packard  /   Enhanced by   NTU Library IR team Copyright ©   - Feedback