Solving Fractional Differential Equations by Using Triangle Neural Network

In this paper, numerical methods for solving fractional differential equations by using a triangle neural network are proposed. The derivative is considered Caputo type. of the analyzed first. Then, based on technique minimizing loss function network, proposed reduce equation into gradient descent problem or quadratic optimization problem. By process process, solution to FDEs can be obtained. efficiency and accuracy presented shown some examples. Numerical tests show that approach easy implement accurate when applied many types FDEs.