ANALYSIS OF LEARNING-PROCESSES OF CHAOTIC TIME-SERIES BY NEURAL NETWORKS
Citation
T. Hondou et Y. Sawada, ANALYSIS OF LEARNING-PROCESSES OF CHAOTIC TIME-SERIES BY NEURAL NETWORKS, Progress of theoretical physics, 91(2), 1994, pp. 397-402
Categorie Soggetti
Physics
SICI code
0033-068X(1994)91:2<397:AOLOCT>2.0.ZU;2-7
Abstract
Study of the learning process of chaotic time series by neural network
s with back-propagation algorithm showed the existence of a general le
arning process. The process was found to be efficiently characterized
by newly defined normalized measures, the coherence and the direction-
cosine for the motion of weight vectors.
