solving optimal control problems using sigmoid-weighted neural networks

In this study, we are motivated to obtain the solution of optimal controlproblems via universal approximation capability of a single-layer feedfor-ward articial neural network. first, we transform the optimal controlproblems into systems of dierential equations. then, we solve these sys-tems using a single-layer feedforward sigmoid-weighted neural network.optimal control problemhamiltonian control systemsystem of ordinarydierential equations approximate solutions error back propagation