Predictive neural fields for improved tracking and attentional properties

Jean-Charles Quinton 1 Bernard Girau 1
1 CORTEX - Neuromimetic intelligence
INRIA Lorraine, LORIA - Laboratoire Lorrain de Recherche en Informatique et ses Applications
Abstract : Predictive capabilities are added to the competition mechanism known as the Continuum Neural Field Theory, in order to improve and extend its attentional properties. In order to respect the distributed and bio-inspired nature of the model, the prediction is introduced as an internal stimulation, directly determined by the past field activity. Building on mathematical developments and optimization techniques, performance is ascertained on a 2D tracking application where the system must robustly focus on a target despite rapid movements, noise and distracters. In addition to a consistent gain on previously observed capabilities, the extended model can also track stimuli with full occlusions and static obstacles on the trajectory.
Type de document :
Communication dans un congrès
International Joint Conference on Neural Networks IJCNN 2011, Jul 2011, San José, United States. IEEE Computational Intelligence Society, 2011, The 2011 International Joint Conference on Neural Networks
Liste complète des métadonnées

Littérature citée [17 références]  Voir  Masquer  Télécharger

https://hal.inria.fr/inria-00603902
Contributeur : Jean-Charles Quinton <>
Soumis le : lundi 27 juin 2011 - 17:31:55
Dernière modification le : jeudi 11 janvier 2018 - 06:19:48
Document(s) archivé(s) le : mercredi 28 septembre 2011 - 02:26:54

Fichier

prediction.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

  • HAL Id : inria-00603902, version 1

Collections

Citation

Jean-Charles Quinton, Bernard Girau. Predictive neural fields for improved tracking and attentional properties. International Joint Conference on Neural Networks IJCNN 2011, Jul 2011, San José, United States. IEEE Computational Intelligence Society, 2011, The 2011 International Joint Conference on Neural Networks. 〈inria-00603902〉

Partager

Métriques

Consultations de la notice

357

Téléchargements de fichiers

230