DocumentCode
1842687
Title
Curved search algorithm for neural network learning
Author
Wu, Peitsang ; Fang, Shu-Cherng ; Nuttle, Henry L W
Author_Institution
Dept. of Ind. Manage., I-Shou Univ., Kaohsiung, Taiwan
Volume
3
fYear
1999
fDate
1999
Firstpage
1733
Abstract
In this paper we present a new learning method of back propagation training algorithms for neural networks. With the objective of reducing training time, we introduce a curved search method with a fixed step size for determining weight adjustments. Computational results indicate a strong potential for significant reduction in training time
Keywords
backpropagation; computational complexity; multilayer perceptrons; search problems; back propagation training algorithms; backpropagation training algorithms; curved search algorithm; fixed step size; neural network learning; training time reduction; weight adjustments; Engineering management; Feedforward neural networks; Industrial training; Learning systems; Management training; Multi-layer neural network; Neural networks; Neurons; Newton method; Search methods;
fLanguage
English
Publisher
ieee
Conference_Titel
Neural Networks, 1999. IJCNN '99. International Joint Conference on
Conference_Location
Washington, DC
ISSN
1098-7576
Print_ISBN
0-7803-5529-6
Type
conf
DOI
10.1109/IJCNN.1999.832638
Filename
832638
Link To Document