An adaptive conjugate gradient learning algorithm for efficient training of neural networks

H. Adeli*, Shih-Lin Hung

*此作品的通信作者

研究成果: Article同行評審

129 引文 斯高帕斯(Scopus)

摘要

An adaptive conjugate gradient learning algorithm has been developed for training of multilayer feedforward neural networks. The problem of arbitrary trial-and-error selection of the learning and momentum ratios encountered in the momentum backpropagation algorithm is circumvented in the new adaptive algorithm. Instead of constant learning and momentum ratios, the step length in the inexact line search is adapted during the learning process through a mathematical approach. Thus, the new adaptive algorithm provides a more solid mathematical foundation for neural network learning. The algorithm has been implemented in C on a SUN-SPARCstation and applied to two different domains: engineering design and image recognition. It is shown that the adaptive neural networks algorithm has superior convergence property compared with the momentum backpropagation algorithm.

原文English
頁(從 - 到)81-102
頁數22
期刊Applied Mathematics and Computation
62
發行號1
DOIs
出版狀態Published - 4月 1994

指紋

深入研究「An adaptive conjugate gradient learning algorithm for efficient training of neural networks」主題。共同形成了獨特的指紋。

引用此