A Variational Formulation for the Multilayer Perceptron

  • Roberto Lopez
  • Eugenio Oñate
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4131)

Abstract

In this work we present a theory of the multilayer perceptron from the perspective of functional analysis and variational calculus. Within this formulation, the learning problem for the multilayer perceptron lies in terms of finding a function which is an extremal for some functional. As we will see, a variational formulation for the multilayer perceptron provides a direct method for the solution of general variational problems, in any dimension and up to any degree of accuracy. In order to validate this technique we use a multilayer perceptron to solve some classical problems in the calculus of variations.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Weisstein, E.W.: MathWorld - A Wolfram Web Resource (2006), http://mathworld.wolfram.com
  2. 2.
    Elsgolc, L.E.: Calculus of Variations. Pergamon Press, Oxford (1961)MATHGoogle Scholar
  3. 3.
    Bishop, C.: Neural Networks for Pattern Recognition. Oxford University Press, Oxford (1995)Google Scholar
  4. 4.
    Šíma, J., Orponen, P.: General-Purpose Computation with Neural Networks: A Survey of Complexity Theoretic Results. Neural Computation 15, 2727–2778 (2003)MATHCrossRefGoogle Scholar
  5. 5.
    Lopez, R., Balsa-Canto, E., Oñate, E.: Artificial Neural Networks for the Solution of Optimal Control Problems. In: Proceedings of the Sixth Conference on Evolutionary and Deterministic Methods for Design, Optimisation and Control with Applications to Industrial and Societal Problems (2005)Google Scholar
  6. 6.
    Hornik, K., Stinchcombe, M., White, H.: Multilayer feedforward networks are universal approximators. Neural Networks 2-5, 359–366 (1989)CrossRefGoogle Scholar
  7. 7.
    Dadvand, P., Lopez, R., Oñate, E.: Artificial Neural Networks for the Solution of Optimal Control Problems. In: Proceedings of the International Conference ERCOFTAC (2006)Google Scholar
  8. 8.
    Lopez, R.: Flood: An Open Source Neural Networks C++ Library (2005), http://www.cimne.com/flood
  9. 9.
    Stoer, J., Bulirsch, R.: Introduction to Numerical Analysis. Springer, Heidelberg (1980)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Roberto Lopez
    • 1
  • Eugenio Oñate
    • 1
  1. 1.International Center for Numerical Methods in Engineering (CIMNE)Technical University of Catalonia (UPC)BarcelonaSpain

Personalised recommendations