Optimal Brain Surgeon Variants for Optimization - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2004

Optimal Brain Surgeon Variants for Optimization

Mohammed Attik
  • Function : Author
  • PersonId : 830959
Laurent Bougrain
Frédéric Alexandre


The determination of the optimal architecture of a multilayer perceptron (MLP) to solve a specific problem is an important and a difficult task. Several approaches based on saliency analysis, such as the Optimal Brain Surgeon method (OBS), have been developed in this field. Nevertheless, we show in this paper that OBS does not gives an optimal architecture. We also present the advantages of applying OBS on the architecture obtained by a variable selection method. New hybrid methods are proposed. A comparison of our approaches to standard techniques for architecture optimization is presented Simulation results obtained on the Monk's problem illustrate the specificities of each method described in this paper.
Fichier principal
Vignette du fichier
A04-R-459.pdf (145.09 Ko) Télécharger le fichier

Dates and versions

inria-00099924 , version 1 (26-09-2006)


  • HAL Id : inria-00099924 , version 1


Mohammed Attik, Laurent Bougrain, Frédéric Alexandre. Optimal Brain Surgeon Variants for Optimization. 16h European Conference on Artificial Intelligence - ECAI'04, 2004, Valencia, Spain, 2 p. ⟨inria-00099924⟩
260 View
70 Download


Gmail Facebook X LinkedIn More