DocumentCode :
3565798
Title :
Optimizing multilayer neural networks using fractal dimensions of time-series data
Author :
Matsuba, Ikuo ; Masui, Hironari ; Hebishima, Shingo
Author_Institution :
Hitachi Ltd., Kawasaki, Japan
Volume :
1
fYear :
1992
Firstpage :
583
Abstract :
A fractal dimension of time-series data is used to optimize a three-layer feedback neural network which was proposed previously to detect an important time structure of time-series data and to predict a future sequence based on a current input sequence. Optimization means in a sense that the prediction error is minimized. A time interval giving the same fractal dimensions is used as an optimal size of the output layer. The number of input units is twice the number of output units. It is also found that reliability in prediction is determined empirically as a function of the fractal dimension
Keywords :
fractals; neural nets; optimisation; time series; fractal dimension; prediction; three-layer feedback neural network; time-series data; Artificial neural networks; Control systems; Fractals; Frequency; Laboratories; Linear approximation; Multi-layer neural network; Neural networks; Power generation economics; Random processes;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Neural Networks, 1992. IJCNN., International Joint Conference on
Print_ISBN :
0-7803-0559-0
Type :
conf
DOI :
10.1109/IJCNN.1992.287149
Filename :
287149
Link To Document :
بازگشت