Predicting complex chaotic time series via complex valued MLPs

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.<<ETX>>

[1]  R. Katayama,et al.  Self generating radial basis function as neuro-fuzzy model and its application to nonlinear prediction of chaotic time series , 1993, [Proceedings 1993] Second IEEE International Conference on Fuzzy Systems.

[2]  James D. Keeler,et al.  Layered Neural Networks with Gaussian Hidden Units as Universal Approximations , 1990, Neural Computation.

[3]  Omid M. Omidvar.  Progress in neural networks , 1991 .

[4]  George Cybenko,et al.  Approximation by superpositions of a sigmoidal function , 1992, Math. Control. Signals Syst..

[5]  D.R. Hush,et al.  Progress in supervised neural networks , 1993, IEEE Signal Processing Magazine.

[6]  K. Ikeda,et al.  Optical Turbulence: Chaotic Behavior of Transmitted Light from a Ring Cavity , 1980 .

[7]  Robert M. Farber,et al.  How Neural Nets Work , 1987, NIPS.

[8]  Luigi Fortuna,et al.  On the capability of neural networks with complex neurons in complex valued functions approximation , 1993, 1993 IEEE International Symposium on Circuits and Systems.

[9]  Francesco Piazza,et al.  On the complex backpropagation algorithm , 1992, IEEE Trans. Signal Process..

[10]  Henry Leung,et al.  The complex backpropagation algorithm , 1991, IEEE Trans. Signal Process..