University of Sistan and BaluchestanIranian Journal of Fuzzy Systems1735-065411120140225Numerical solution of fuzzy linear Fredholm integro-differential equation by \fuzzy neural network91112139710.22111/ijfs.2014.1397ENMaryam MoslehDepartment of Mathematics, Firoozkooh Branch, Islamic Azad Uni-
versity, Firoozkooh, IranJournal Article20111026In this paper, a novel hybrid method based on learning algorithm<br />of fuzzy neural network and Newton-Cotes<br />methods with positive coefficient for the solution of linear Fredholm<br /> integro-differential equation of the second kind<br />with fuzzy initial value is presented. Here neural network is<br />considered as a part of large field called neural computing or<br />soft computing. We propose a<br />learning algorithm from the cost function for adjusting fuzzy<br />weights. This paper is one of the first attempts to derive learning<br />algorithms from fuzzy neural networks with real input, fuzzy output,<br />and fuzzy weights. Finally, we illustrate our approach by numerical examples.http://ijfs.usb.ac.ir/article_1397_1e44bcaee4c0a281eafa46bae01a2651.pdf