Oscillation Characteristics of the Multi-stage Learning for the Layered Neural Networks and Its Analysis
This paper proposes an efficient learning method for the layered neural networks based on the selection of training data and input characteristics of an output layer unit. The multi-stage learning method proposes by the authors for the function approximation problems of classifying learning data in a phased manner, focusing on their learnabilities prior to learning in the multi layered neural network, and demonstrates validity of the multi-stage learning method. Specifically, this paper verifies by computer experiments that both of larning accuracy and learning time are improved of the BP method as a learning rule of the multi-stage learning method. The authors also discuss the occurrence mechanisms of oscillatory phenomena in learning. Furthermore, the authors discuss the reasons that errors of some data remain large value even after learning, observing behaviors during learning.
Keywords: data selection, function approximation problem, multi-stage leaning, neural network, voluntary oscillation.
Download Full-Text
ABOUT THE AUTHORS
Isao Taguch
1--5--21, Anagawa, Inage-ku, Chiba-shi, 263-8588, Japan
Yasuo Sugai
1-33, Yayoi-cho, Inage-ku, Chiba-shi, 263-8522, Japan
Isao Taguch
1--5--21, Anagawa, Inage-ku, Chiba-shi, 263-8588, Japan
Yasuo Sugai
1-33, Yayoi-cho, Inage-ku, Chiba-shi, 263-8522, Japan