R. López, E. Oñate
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.
Keywords:
Published on 01/01/2008
DOI: 10.1016/j.neucom.2007.12.037Licence: CC BY-NC-SA license
Times cited: 1Views 4Recommendations 0
Are you one of the authors of this document?