HAL will be down for maintenance from Friday, June 10 at 4pm through Monday, June 13 at 9am. More information
Skip to Main content Skip to Navigation
Conference papers

How to speed up the training mechanism in a connectionist model

Szilárd Vajda 1 Abdel Belaïd 1
LORIA - Laboratoire Lorrain de Recherche en Informatique et ses Applications
Abstract : In this paper a fast data driven learning-corpus building algorithm (FDDLCB) is proposed. The generic technique allows to build dynamically a representative and compact learning corpus for a connectionist model. The constructed dataset contains just a reduced number of patterns but sufficiently descriptive to characterize the different classes which should be separated. The method is based on a double least mean squares (LMS) error minimization mechanism trying to find the optimal boundaries of the different pattern classes. In the classical learning process the LMS is serving to minimize the error during the learning and this process is improved with a second one, as the new samples selection is also based on the idea to minimize the recognition error. Reinforcing the class boundaries where the recognition fails let us achieve a rapid and good generalization without any loss of occuracy. A modified version of the algorithm will be also presented. The experiments were performed on MNIST (Modified NIST) separated digit dataset. The encouraging result (98.51%) using just 1.85% of the available patterns from the original training dataset is comparable even with the state of the art techniques.
Complete list of metadata

Cited literature [21 references]  Display  Hide  Download

Contributor : Szilard Vajda Connect in order to contact the contributor
Submitted on : Tuesday, September 27, 2005 - 2:51:17 PM
Last modification on : Friday, February 26, 2021 - 3:28:06 PM
Long-term archiving on: : Wednesday, March 29, 2017 - 11:46:13 AM


 Restricted access
To satisfy the distribution rights of the publisher, the document is embargoed until : jamais

Please log in to resquest access to the document


  • HAL Id : inria-00000358, version 1



Szilárd Vajda, Abdel Belaïd. How to speed up the training mechanism in a connectionist model. IAPR - TC3 International Workshop on Neural Networks and Learning in Document Recognition - NNLDAR 2005, Aug 2005, Seoul/Korea, pp.13-17. ⟨inria-00000358⟩



Record views