Deep neural network for solving stochastic biological systems

In this study, we present deep neural network method (DNN) for nding nu- merical solution of a class of stochastic biological systems. DNN utilizes Morgan-Voyce Even Lucas polynomials and sinh function as activation functions of the Deep struc- ture. The standard Brownian motion, the Gauss-Legendre quadrature and the classical optimization method are applied to train this neural network. Finally, the numerical technique is implemented for a stochastic biological system to illustrate the superiority and e ciency of the proposed method.