You do not have permission to edit this page, for the following reason:
You can view and copy the source of this page.
Published in ''Neurocomputing'' Vol. 71 (13-15), pp. 2538-2543, 2008<br />
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.
<pdf>Media:Draft_Samper_874023138_7534_1-s2.0-S0925231208002166-main.pdf</pdf>
Return to Lopez Onate 2008a.