Artificial Neural Network Technique for Solving Variable Order Fractional Integro-Differential Algebraic Equations

In this paper, we will use an artificial neural network (ANN) to solve the variable order fractional integro-differential algebraic equations (VFIDAEs), which is a three-layer feed-forward architecture that formed and trained using back propagation unsupervised learning algorithm based on gradient descent rule for minimizing error function parameter modification (weights biases).When combine initial conditions with ANN output, get good approximation of VFIDAE solution. Finally, analysis complemented by two numerical examples demonstrate method capability. The collected results show suggested strategy quite successful, resulting in superior approximations these cases.