標題: Quadratic optimization method for multilayer neural networks with local error-backpropagation
作者: Liu, CS
Tseng, CH
機械工程學系
Department of Mechanical Engineering
公開日期: 1-八月-1999
摘要: A fast new local error-backpropagation (LBP) algorithm is presented for the training of multilayer neural networks. This algorithm is based on the definition of a new local mean-squared error function. If the local desired outputs have been estimated, the multilayer neural networks can be decomposed into a set of adaptive linear elements (Adaline) that can be trained by quadratic optimization methods. Among a lot of quadratic optimization methods, the conjugate gradient (CG) method is one of the most famous methods that can find the global optimal solution of quadratic problems within finite steps. The iteration number and the computation time are significantly reduced because the stepsize is computed without line-search. Experimental results on the pattern recognition and memorizing of spatiotemporal patterns are provided.
URI: http://hdl.handle.net/11536/31170
ISSN: 0020-7721
期刊: INTERNATIONAL JOURNAL OF SYSTEMS SCIENCE
Volume: 30
Issue: 8
起始頁: 889
結束頁: 898
顯示於類別:Articles


Files in This Item:

  1. 000082105600008.pdf

If it is a zip file, please download the file and unzip it, then open index.html in a browser to view the full text content.