Logo LVSN
EnglishAccueil
A proposPersonnesRecherchePublicationsEvenementsProfil
A propos
Publications

 

 

 

 

CERVIM

REPARTI

MIVIM

An Hybrid Architecture for Active and Incremental Learning: The Self-Organizing Perceptron (SOP) Network


Jean-François Hébert, Marc Parizeau and Nadia Ghazzali


Abstract - This paper describes a new hybrid architecture for an artificial neural network classifier that enables incremental learning. The learning algorithm of the proposed architecture detects the occurrence of unknown data and automatically adapts the structure of the network to learn these new data, without degrading previous knowledge. The architecture combines an unsupervised self-organizing map with a supervised Perceptron network to form the Self-Organizing Perceptron network (SOP).

download document

Bibtex:

@inproceedings{Hébert51,
    author    = { Jean-François Hébert and Marc Parizeau and Nadia Ghazzali },
    title     = { An Hybrid Architecture for Active and Incremental Learning: The Self-Organizing Perceptron (SOP) Network },
    booktitle = { Proc. of the International Joint Conference on Neural Networks (IJCNN) },
    pages     = { 1646-1651 },
    year      = { 1999 },
    month     = { July },
    location  = { Washington DC (U.S.A.) }
}

Dernière modification: 2002/06/14 par parizeau

     
   
   

©2002-. Laboratoire de Vision et Systèmes Numériques. Tous droits réservés