Infinite-dimensional multilayer perceptrons

Kuzuoglu M., Leblebicioglu K.

IEEE TRANSACTIONS ON NEURAL NETWORKS, vol.7, no.4, pp.889-896, 1996 (SCI-Expanded) identifier identifier identifier

  • Publication Type: Article / Article
  • Volume: 7 Issue: 4
  • Publication Date: 1996
  • Doi Number: 10.1109/72.508932
  • Journal Name: IEEE TRANSACTIONS ON NEURAL NETWORKS
  • Journal Indexes: Science Citation Index Expanded (SCI-EXPANDED), Scopus, Academic Search Premier, Applied Science & Technology Source, Business Source Elite, Business Source Premier, Computer & Applied Sciences
  • Page Numbers: pp.889-896
  • Middle East Technical University Affiliated: Yes

Abstract

In this paper a new multilayer perceptron (MLP) structure is introduced to simulate nonlinear transformations on infinite-dimensional function spaces. This extension is achieved by replacing discrete neurons by a continuum of neurons, summations by integrations and weight matrices by kernels of integral transforms, Variational techniques have been employed for the analysis and training of the infinite-dimensional MLP (IDMLP). The training problem of IDMLP is solved by the Lagrange multiplier technique yielding the coupled state and adjoint state integro-difference equations. A steepest descent-like algorithm is used to construct the required kernel and threshold functions. Finally, some results are presented to show the performance of the new IDMLP.