Fuzzy set similarity using kernels on fuzzy sets
Résumé
—This paper presents a new kernel on fuzzy sets: the cross product kernel on fuzzy sets which can be used to estimate similarity measures between fuzzy with a geometrical interpretation in terms of inner products. We show that that kernel is a particular case of the convolution kernel and it generalize the widely-know kernel on sets towards the space of fuzzy sets. Moreover, we show that the cross product kernel on fuzzy sets performs an embedding of probability measures into a reproduction kernel Hilbert space. Finally, we experimentally show the applicability and power of this kernel on a supervised classification task on noisy datasets. Index Terms—Kernel on fuzzy sets, similarity measures on fuzzy sets, kernel on sets.
Domaines
Apprentissage [cs.LG]
Origine : Fichiers produits par l'(les) auteur(s)