Abstract
A new fuzzy neural network model was presented based on the fuzzy arithmetic of polygonal fuzzy numbers and a new extension principle.When the inputs are negative,the relevant feed-forward three-layer polygonal fuzzy neural networks were proved to be universal approximators of continuous fuzzy functions.The equivalent condition under which the fuzzy function universal approximated by the polygonal FNN should be satisfied was given.A simulation example was introduced in the end.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have