A Stabilizing and Robustifying Training Scheme for Artificial Neural Networks Used in Control of Complex Systems

This paper presents a method for stabilizing and robustifying the artificial neural networks trained by utilizing the gradient descent. The method proposed constructs a dynamic model of the conventional update mechanism and derives the stabilizing values of the learning rate. The stability in this context corresponds to the convergence in adjustable parameters of the neural network structure. It is shown that the selection of the learning rate as imposed by the proposed algorithm results in stable training in the sense of Lyapunov. Furthermore, the algorithm devised filters out the high frequency dynamics of the gradient descent method. The method analyzed in this paper integrates the gradient descent technique with variable structure systems methodology. In the simulations, control of a three degrees of freedom anthropoid robot is chosen for the evaluation of the performance.