Publications [#289450] of Silvia Ferrari

Papers Published

1. Ferrari, S; Stengel, RF, Algebraic training of a neural network, Proceedings of the American Control Conference, vol. 2 (January, 2001), pp. 1605-1610, IEEE [doi]
   (last updated on 2021/09/05)

   Abstract:
   A novel algebraic neural network training technique is developed and demonstrated on two well-known architectures. This approach suggests an innovative, unified framework for analyzing neural approximation properties and for training neural networks in a much simplified way. Various implementations show that this approach presents numerous practical advantages; it provides a trouble-free non-iterative systematic procedure to integrate neural networks in control architectures, and it affords deep insight into neural nonlinear control system design.