Abstract
New open box and nonlinear model of Ultra High Frequency Polynomial and Cosine Artificial Higher Order Neural Network (UPC-HONN) is presented in this paper. A new learning algorithm for UPC-HONN is also developed from this study. A time series data simulation and analysis system, UPC-HONN Simulator, is built based on the UPC-HONN models too. Test results show that average error of UPC-HONN models are closing to zero (0.0000%). The average errors of Polynomial Higher Order Neural Network (PHONN), Trigonometric Higher Order Neural Network (THONN), and Sigmoid polynomial Higher Order Neural Network (SPHONN) models are from 2.8546% to 3.4185%. It means that UPC-HONN models are 2.8546% to 3.4185% better than PHONN, THONN, and SPHONN models.
Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
