PerTurbo: a new classification algorithm based on the spectrum perturbations of the Laplace-Beltrami operator - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2011

PerTurbo: a new classification algorithm based on the spectrum perturbations of the Laplace-Beltrami operator

Résumé

PerTurbo, an original, non-parametric and efficient classification method is presented here. In our framework, the manifold of each class is characterized by its Laplace-Beltrami operator, which is evaluated with classical methods involving the graph Laplacian. The classification criterion is established thanks to a measure of the magnitude of the spectrum perturbation of this operator. The first experiments show good performances against classical algorithms of the state-of-the-art. Moreover, from this measure is derived an efficient policy to design sampling queries in a context of active learning. Performances collected over toy examples and real world datasets assess the qualities of this strategy.

Dates et versions

hal-00599684 , version 1 (10-06-2011)

Identifiants

Citer

Nicolas Courty, Thomas Burger, Laurent D. Johann. PerTurbo: a new classification algorithm based on the spectrum perturbations of the Laplace-Beltrami operator. ECML-PKDD 2011, 2011, Athens, Greece. ⟨10.1007/978-3-642-23780-5_33⟩. ⟨hal-00599684⟩
152 Consultations
0 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More