RBF networks vs. multilayer perceptrons for sequence recognition

Michele Ceccarelli, Joel T. Hounsou

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Citation (Scopus)

Abstract

In this paper we consider several learning procedures for Radial Basis Function Networks applied to a problem of speech recognition. The dynamic nature of speech is considered by adding delayed connection and integration units to the network. Our study shows that supervised learning of the centroids of the basis functions gives appreciable results at a significantly small cost. The results thus obtained are compared with the generalization performance of multilayer perceptrons. The possibility to include recurrent connections into RBF networks is also investigated.

Original languageEnglish
Title of host publicationProceedings of the IEEE International Conference on Systems, Man and Cybernetics
Editors Anon
Place of PublicationPiscataway, NJ, United States
PublisherPubl by IEEE
Pages651-656
Number of pages6
Volume2
ISBN (Print)0780309111
Publication statusPublished - 1 Dec 1993
Externally publishedYes
EventProceedings of 1993 International Conference on Systems, Man and Cybernetics - Le Touquet, Fr
Duration: 17 Oct 199320 Oct 1993

Other

OtherProceedings of 1993 International Conference on Systems, Man and Cybernetics
CityLe Touquet, Fr
Period17/10/9320/10/93

    Fingerprint

ASJC Scopus subject areas

  • Hardware and Architecture
  • Control and Systems Engineering

Cite this

Ceccarelli, M., & Hounsou, J. T. (1993). RBF networks vs. multilayer perceptrons for sequence recognition. In Anon (Ed.), Proceedings of the IEEE International Conference on Systems, Man and Cybernetics (Vol. 2, pp. 651-656). Publ by IEEE.