標題: Toward a new three layer neural network with dynamical optimal training performance
作者: Wang, Chi-Hsu
Lin, Shu-Fan
電控工程研究所
Institute of Electrical and Control Engineering
關鍵字: neural network;optimal training;iris data
公開日期: 2007
摘要: This paper proposes a revised dynamic optimal training algorithm for a three layer neural network with sigmoid activation function in the hidden layer and linear activation function in the output layer. This three layer neural network can be used for classification problems, such as the classification of Iris data. This revised dynamic optimal training finds optimal learning rate with its upper-bound for next iteration to guarantee optimal convergence of training result. With modification of initial weighting factors and activation functions, revised dynamic optimal training algorithm is more stable and faster than dynamic optimal training algorithm. Excellent improvements of computing time and robustness have been obtained for Iris data set.
URI: http://hdl.handle.net/11536/11390
ISBN: 978-1-4244-0990-7
ISSN: 1062-922X
期刊: 2007 IEEE INTERNATIONAL CONFERENCE ON SYSTEMS, MAN AND CYBERNETICS, VOLS 1-8
起始頁: 3734
結束頁: 3739
顯示於類別:會議論文