Man-Machine Cooperation for the On-Line Training of an Evolving Classifier

Abstract : Touch sensitive interfaces enable new interaction methods, like using gesture commands. To easily memorize more than a dozen of gesture commands, it is important to be able to customize them. The classifier used to recognize drawn symbols must hence be customizable, able to learn from very few data, and evolving, able to learn and improve during its use. This work studies the importance and the impact of using reject to supervise the on-line training of the evolving classifier. The objective is to obtain a gesture command system that cooperates as best as possible with the user: to learn from its mistakes without soliciting him too often. There is a trade-off between the number of user interactions, to supervise the on-line learning, and the number of classification errors, that require a correction from the user.
Type de document :
Communication dans un congrès
IEEE Conference on Evolving and Adaptive Intelligent Systems (EAIS), Jun 2014, Linz, Austria. pp.1-7, 2014, 〈10.1109/EAIS.2014.6867477〉
Liste complète des métadonnées

Littérature citée [14 références]  Voir  Masquer  Télécharger

https://hal.inria.fr/hal-00968257
Contributeur : Manuel Bouillon <>
Soumis le : lundi 31 mars 2014 - 16:58:09
Dernière modification le : vendredi 25 mai 2018 - 01:07:47
Document(s) archivé(s) le : lundi 10 avril 2017 - 07:34:13

Fichier

EAIS2014_Bouillon_Anquetil_PID...
Fichiers produits par l'(les) auteur(s)

Identifiants

Citation

Manuel Bouillon, Eric Anquetil. Man-Machine Cooperation for the On-Line Training of an Evolving Classifier. IEEE Conference on Evolving and Adaptive Intelligent Systems (EAIS), Jun 2014, Linz, Austria. pp.1-7, 2014, 〈10.1109/EAIS.2014.6867477〉. 〈hal-00968257〉

Partager

Métriques

Consultations de la notice

445

Téléchargements de fichiers

121