Partial least-squares algorithm for weights initialization of backpropagation network

Tzu-Chien Hsiao*, Chii Wann Lin, Huihua Kenny Chiang

*Corresponding author for this work

研究成果: Article同行評審

26 引文 斯高帕斯(Scopus)

摘要

This paper proposes a hybrid scheme to set the weights initialization and the optimal number of hidden nodes of the backpropagation network (BPN) by applying the loading weights and factor numbers of the partial least-squares (PLS) algorithm. The joint PLS and BPN method (PLSBPN) starts with a small residual error, modifies the latent weight matrices, and obtains a near-global minimum in the calibration phase. Performances of the BPN, PLS, and PLSBPN were compared for the near infrared spectroscopic analysis of glucose concentrations in aqueous matrices. The results showed that the PLSBPN had the smallest root mean square error. The PLSBPN approach significantly solves some conventional problems of the BPN method by providing the good initial weights, reducing the calibration time, obtaining an optimal solution, and easily determining the number of hidden nodes.

原文English
頁(從 - 到)237-247
頁數11
期刊Neurocomputing
50
DOIs
出版狀態Published - 1 一月 2003

指紋 深入研究「Partial least-squares algorithm for weights initialization of backpropagation network」主題。共同形成了獨特的指紋。

引用此