SciELO - Scientific Electronic Library Online

 
vol.16 issue33Composing music through genetic algorithmsExtradosed bridges: evolution and current trends author indexsubject indexarticles search
Home Pagealphabetic serial listing  

Services on Demand

Journal

Article

Indicators

Related links

  • On index processCited by Google
  • Have no similar articlesSimilars in SciELO
  • On index processSimilars in Google

Share


Tecnura

Print version ISSN 0123-921X

Abstract

GAONA BARRERA, Andrés Eduardo  and  BALLESTEROS LARROTTA, Dora María. An efficient selection of neural-network architectures using pruning and regularization techniques. Tecnura [online]. 2012, vol.16, n.33, pp.158-172. ISSN 0123-921X.

This article shows a detailed comparison of both theoretical and practical Ontogenetic Neural Networks obtained through pruning and regularization algorithms. We initially deal with the concept of a regularized error function and the different ways to modify such a function (weight decay (WD), soft weight sharing, and Chauvin penalty). Then some of the most representative pruning algorithms are considered, particularly the OBD (Optimal Brain Damage) algorithm. We select OBD and WD within the problem of the XOR function with the purpose of analyzing pruning techniques and regularization algorithms. The basic back-propagation algorithm is used in both WD and the inverse Hessian matrix in OBD. According to the results, WD is faster than OBD, but it deletes a smaller number of weights. Additionally, OBD reduces the complexity of the neural-network architecture, but its computational cost is still high.

Keywords : algorithm back-propagation; neural networks; regularization; pruning techniques.

        · abstract in Spanish     · text in Spanish     · Spanish ( pdf )