Gradient-enhanced Neural Network Response Surface Approximations

An approach to develop response surface approximations based upon artificial neural networks trained using both state and sensitivity information is described in this paper. Compared to previous approaches, this approach does not require weighting the residuals of the targets and gradients and is able to approximate gradient-consistent response surfaces with a relatively compact network architecture. Numerical simulation on selected problems is used to evaluate the approach that is implemented with the efficient Levenberg-Marquardt neural network training algorithm. The results show that this gradient-enhanced neural network training approach possesses the capability to develop improved response surface approximations compared to the non-gradient neural network training approach.