FFT Neural Network to Estimate Some Asymmetric Dynamical Maps

The estimation some asymmetric dynamical maps by selecting an appropriate feed forward artificial neural network, transfer function and node weights, is the aim of our paper. Fast Fourier Transform (FFT) as transfer function is used. By means of the mean square error (MSE), the experimental results of proposed algorithm will compared empirically, with the results of the same network but with traditional transfer functions, Logsig and Tagsig. Different cases of the dynamical systems, Asymmetric Logistic, Asymmetric Logistic -Tent and Asymmetric Tent-Logistic are discussed. The performance of proposed algorithm is best from others in all cases from Both sides, speed and accuracy