A Fast Learning Strategy Using Pattern Selection for Feedforward Neural Networks - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2006

A Fast Learning Strategy Using Pattern Selection for Feedforward Neural Networks

Szilárd Vajda
  • Function : Author
  • PersonId : 830136
Yves Rangoni
  • Function : Author
  • PersonId : 830537
Hubert Cecotti
  • Function : Author
  • PersonId : 830534
Abdel Belaïd
  • Function : Author
  • PersonId : 830137

Abstract

Intelligent pattern selection is an active learning strategy where the classifiers select during training the most informative patterns. This paper investigates such a strategy where the informativeness of a pattern is measured as the approximation error produced by the classifier. The algorithm builds the training corpus starting from a small randomly chosen initial dataset and new patterns are added to the learning corpus based on their error sensitivity. The training dataset expansion is based on the selection of the most erroneous patterns. Our experimental results on MNIST 1 separated digit dataset show that only 3.26%of training data are sufficient for training purpose without decreasing the performance (98.36%) of the resulting neural classifier.
Fichier principal
Vignette du fichier
cr1109240398082.pdf (174.04 Ko) Télécharger le fichier
Loading...

Dates and versions

inria-00104833 , version 1 (09-10-2006)

Identifiers

  • HAL Id : inria-00104833 , version 1

Cite

Szilárd Vajda, Yves Rangoni, Hubert Cecotti, Abdel Belaïd. A Fast Learning Strategy Using Pattern Selection for Feedforward Neural Networks. Tenth International Workshop on Frontiers in Handwriting Recognition 2006 - IWFHR'10, Université de Rennes 1, Oct 2006, La Baule, France. pp.6. ⟨inria-00104833⟩
115 View
86 Download

Share

Gmail Facebook Twitter LinkedIn More