An extended class of multilayer perceptron

Authors:
R. Lopez;E. Oñate
Affiliations:
International Center for Numerical Methods in Engineering (CIMNE), Edificio C1, Gran Capitán s/n, 08034 Barcelona, Spain;International Center for Numerical Methods in Engineering (CIMNE), Edificio C1, Gran Capitán s/n, 08034 Barcelona, Spain
Venue:
Neurocomputing
Year:
2008

Citing 7
Cited 0

Multilayer feedforward networks are universal approximators

Neural Networks
An introduction to the mathematical theory of inverse problems

An introduction to the mathematical theory of inverse problems
Neural Networks for Pattern Recognition

Neural Networks for Pattern Recognition
General-purpose computation with neural networks: a survey of complexity theoretic results

Neural Computation
A variational formulation for the multilayer perceptron

ICANN'06 Proceedings of the 16th international conference on Artificial Neural Networks - Volume Part I
No free lunch theorems for optimization

IEEE Transactions on Evolutionary Computation
An introduction to simulated evolutionary optimization

IEEE Transactions on Neural Networks

Quantified Score

Hi-index	0.01

Visualization

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.