Title :
Predicting complex chaotic time series via complex valued MLPs
Author :
Arena, P. ; Fortuna, L. ; Xibilia, M.G.
Author_Institution :
Dipartimento Elettrico Elettronico e Sistemistico, Catania Univ., Italy
fDate :
30 May-2 Jun 1994
Abstract :
In the paper it is proposed the use of a complex valued multi-layer perceptron neural network (MLP) with complex activation functions and complex connection strengths in order to perform the estimation of chaotic time series. In particular, the Ikeda map is taken into consideration. A comparison between the behavior of the real MLP and the complex one is also reported, showing that the complex valued MLP requires a smaller topology as well as a lower number of parameters in order to reach comparable performance
Keywords :
estimation theory; multilayer perceptrons; time series; Ikeda map; complex activation functions; complex chaotic time series prediction; complex connection strengths; complex valued MLP; multilayer perceptron neural network; Chaos; Chemistry; Inverse problems; Multi-layer neural network; Multilayer perceptrons; Neural networks; Nonlinear equations; Predictive models; Signal processing; Topology;
Conference_Titel :
Circuits and Systems, 1994. ISCAS '94., 1994 IEEE International Symposium on
Conference_Location :
London
Print_ISBN :
0-7803-1915-X
DOI :
10.1109/ISCAS.1994.409519
