A generative-discriminative learning model for noisy information fusion

Thomas Hecht 1 Alexander Gepperth 1, 2
2 Flowers - Flowing Epigenetic Robots and Systems
Inria Bordeaux - Sud-Ouest, U2IS - Unité d'Informatique et d'Ingénierie des Systèmes
Abstract : This article is concerned with the acquisition of multimodal integration capacities by learning algorithms. Humans seem to perform statistically optimal fusion, and this ability may be gradually learned from experience. In order to stress the advantage of learning approaches in contrast to hand-coded models, we propose a generative-discriminative learning architecture that avoids simplifying assumptions on prior distributions and copes with realistic relationships between observations and underlying values. We base our investigation on a simple self-organized approach, for which we show statistical near-optimality properties by explicit comparison to an equivalent Bayesian model on a realistic artificial dataset.
Document type :
Conference papers
Liste complète des métadonnées

Contributor : Alexander Gepperth <>
Submitted on : Wednesday, January 6, 2016 - 2:51:41 PM
Last modification on : Friday, December 8, 2017 - 2:42:16 PM
Document(s) archivé(s) le : Thursday, April 7, 2016 - 3:49:42 PM


Files produced by the author(s)



Thomas Hecht, Alexander Gepperth. A generative-discriminative learning model for noisy information fusion. International Conference on Development and Learning (ICDL), Aug 2015, Providence, United States. ⟨10.1109/DEVLRN.2015.7346148⟩. ⟨hal-01250967⟩



Record views


Files downloads