An extended class of multilayer perceptron

Published in Neurocomputing, Vol. 71 (13-15), pp. 2538-2543, 2008
DOI: 10.1016/j.neucom.2007.12.037

Abstract

In this work an extended class of multilayer perceptron is presented. This includes independent parameters, boundary conditions and lower and upper bounds. In some cases, such extensions contain a priori information of the problem. On some other situations they are necessary in order to define a correct representation for the solution.

The use of this augmented class of neural network is illustrated through a case study in the optimal control theory. The numerical results are compared against the analytical solution.