Share Email Print

Proceedings Paper

The application of optimal weights initialization algorithm based on K-L transform in multi-layer perceptron networks
Author(s): Wei Xiao; Dun Pu; Zhicheng Dong; Cungen Liu
Format Member Price Non-Member Price
PDF $14.40 $18.00
cover GOOD NEWS! Your organization subscribes to the SPIE Digital Library. You may be able to download this paper for free. Check Access

Paper Abstract

The paper presents a novel method of initial weights optimization method in Multi-Layer Perceptron Network(MLPN). Firstly, the sample sets should be transformed by K-L Transform. Secondly, use K-L Converting Matrix to initialize the weights between input and hidden layer. Thirdly the MLPN is trained by BP algorithm, and the convergence speed of MLPN is improved evidently. The ultimate test shows the new algorithm is suitable for the situation of low-dimensional data.

Paper Details

Date Published: 19 July 2013
PDF: 4 pages
Proc. SPIE 8878, Fifth International Conference on Digital Image Processing (ICDIP 2013), 88784O (19 July 2013); doi: 10.1117/12.2031954
Show Author Affiliations
Wei Xiao, Tibet Univ. (China)
Wuhan Univ. (China)
Dun Pu, Tibet Univ. (China)
Zhicheng Dong, Tibet Univ. (China)
Cungen Liu, Shandong Jianzhu Univ. (China)

Published in SPIE Proceedings Vol. 8878:
Fifth International Conference on Digital Image Processing (ICDIP 2013)
Yulin Wang; Xie Yi, Editor(s)

© SPIE. Terms of Use
Back to Top