A cognitive stochastic machine based on Bayesian inference: a behavioral analysis

Raphael Frisch 1, 2 Marvin Faix 2 Emmanuel Mazer 2 Laurent Fesquet 1 Augustin Lux 2
2 PERVASIVE - Interaction située avec les objets et environnements intelligents
Inria Grenoble - Rhône-Alpes, Université de Grenoble-Alpes, LIG - Laboratoire d'Informatique de Grenoble, Grenoble INP - Institut polytechnique de Grenoble - Grenoble Institute of Technology
Abstract : Bayesian models and stochastic computing form a promising paradigm for non-conventional, bio-inspired computation architectures. In particular, they are able to handle uncertainty and promise low power consumption. In this paper we study the application of such an architecture, the Sliced Bayesian Machine (SlicedBM) to a real-world problem, Sound Source Localization (SSL) for robots. We present an analysis of the quality of results and of computing time according to several parameters: sensor precision, result threshold, internal word length. Furthermore, we show that sensor data precision does not heavily influence the computation. On the opposite, the precision of the probability values plays an important role on result quality. This parameter also determines the circuit size. We also show that the higher the re-sampling threshold (RT), the better the distribution computed by the machine. Our results make it possible to choose optimal design parameters for a circuit along several trade-offs, and according to a given sensor fusion application.
Type de document :
Communication dans un congrès
ICCI*CC 2018 - 17th IEEE International Conference on Cognitive Informatics and Cognitive Computing, Jul 2018, Berkeley, United States. pp.1-8
Liste complète des métadonnées

https://hal.archives-ouvertes.fr/hal-01867789
Contributeur : Raphael Frisch <>
Soumis le : mardi 4 septembre 2018 - 16:01:11
Dernière modification le : vendredi 14 septembre 2018 - 10:36:17

Fichier

2018-iccicc.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

  • HAL Id : hal-01867789, version 1

Citation

Raphael Frisch, Marvin Faix, Emmanuel Mazer, Laurent Fesquet, Augustin Lux. A cognitive stochastic machine based on Bayesian inference: a behavioral analysis. ICCI*CC 2018 - 17th IEEE International Conference on Cognitive Informatics and Cognitive Computing, Jul 2018, Berkeley, United States. pp.1-8. 〈hal-01867789〉

Partager

Métriques

Consultations de la notice

104

Téléchargements de fichiers

45