PROPRE: PROjection and PREdiction for multimodal correlations learning. An application to pedestrians visual data discrimination - ENSTA Paris - École nationale supérieure de techniques avancées Paris Accéder directement au contenu
Communication Dans Un Congrès Année : 2014

PROPRE: PROjection and PREdiction for multimodal correlations learning. An application to pedestrians visual data discrimination

Résumé

PROPRE is a generic and modular unsupervised neural learning paradigm that extracts meaningful concepts of multimodal data flows based on predictability across modalities. It consists on the combination of three modules. First, a topological projection of each data flow on a self-organizing map. Second, a decentralized prediction of each projection activity from each others map activities. Third, a predictability measure that compares predicted and real activities. This measure is used to modulate the projection learning so that to favor the mapping of predictable stimuli across modalities. In this article, we use Kohonen map for the projection module, linear regression for the prediction one and we propose multiple generic predictability measures. We illustrate the properties and performances of PROPRE paradigm on a challenging supervised classification task of visual pedestrian data. The modulation of the projection learning by the predictability measure improves significantly classification performances of the system independently of the measure used. Moreover, PROPRE provides a combination of interesting functional properties, such as a dynamical adaptation to input statistic variations, that is rarely available in other machine learning algorithms.
Fichier principal
Vignette du fichier
final_article.pdf (3.14 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-01061662 , version 1 (08-09-2014)

Identifiants

  • HAL Id : hal-01061662 , version 1

Citer

Mathieu Lefort, Alexander Gepperth. PROPRE: PROjection and PREdiction for multimodal correlations learning. An application to pedestrians visual data discrimination. IJCNN - International Joint Conference on Neural Networks, Jul 2014, Pékin, China. ⟨hal-01061662⟩
147 Consultations
171 Téléchargements

Partager

Gmail Facebook X LinkedIn More