Neural Network Estimation of Some Noisy Asymmetric Dynamical Maps with Use FFT as Transfer Function
Salah H. Abid, Saad Shakir Mahmood, Yaseen Adel Oraibi · 2019
The aim of this paper is to design a feed forward artificial neural network (Ann) to estimate one dimensional noisy Asymmetric dynamical map by selecting an appropriate network, transfer function and node weights to get noisy Asymmetric dynamical map estimation. The proposed network side by side with using Fast Fourier Transform (FFT) as transfer function is used. For different cases of the system, noisy Asymmetric Logistic noisy Asymmetric Logistic -Tent and noisy Asymmetric Tent-Logistic, the experimental results of proposed algorithm will compared empirically, by means of the mean square error (MSE) with the results of the same network but with traditional transfer functions, Logsig and Tagsig. The performance of proposed algorithm is best from others in all cases from Both sides, speed and accuracy.