Sinc and Sigmoid Higher Order Neural Network for Data Modeling and Simulation
Ming Zhang · 2014
New open box and nonlinear model of siNc and Sigmoid Higher Order Neural Network (NS-HONN) is presented in this paper. A new learning algorithm for NS-HONN is also developed from this study. A time series data simulation and analysis system, NS-HONN Simulator, is built based on the NS-HONN models too. Test results show that average error of NS-HONN models are from 2.5081% to 3.6004%, and the average error of Polynomial Higher Order Neural Network (PHONN), Trigonometric Higher Order Neural Network (THONN), and Sigmoid polynomial Higher Order Neural Network (SPHONN) models are from 2.8128% to 4.9076%. It means that NS-HONN models are 0.1162% to 0.4030% better than PHONN, THONN, and SPHONN models