چکیده مقاله
Many real world phenomena with uncertainty can be described as fuzzy differential equations In this paper, we are inspired by a neural network approach toapproximate solutions of linear fuzzy differential equations of first order with initial value under Hukuhara derivative Firstly, we replace the equations with initial value by systems of linear ordinary differential equations Secondly, we solve the systems by single layer feedforward sigmoid weighted neural networks We also demonstrate our method with numerical examples which are extremely accurate compared to the exact solutions
کلیدواژهها
Fuzzy differential equations Artificial neural network Approximate solutions Back propagation System of ordinary differential equations
نویسندگان
Saeed Panahian Fard
Department of Mathematics, Payame Noor University PNU , Tehran, Iran
شیوه ارجاع
Panahian Fard, Saeed,1401,Numerical solutions of fuzzy differential equations using artificial neural networks,10th National Conference on Mathematics, Payame Noor University,Shiraz
ارائهشده در
مجموعه مقالات دهمین همایش ملی ریاضی دانشگاه پیام نور28 اردیبهشت 1401 · شیراز