Exposé de Michael Biehl (University of Groningen) dans le cadre du Data Science Colloqiuum de l'ENS.
This talk briefly reviews important aspects of prototype based systems in the context of supervised learning. A key issue is the choice of an appropriate distance or similarity measure for the task at hand. The powerful framework of relevance learning will be discussed, in which parameterized distance measures are adapted together with the prototypes in the same data-driven training process. Example applications in the bio-medical domain are presented in order to illustrate the concept: (I) the classification of adrenocortical tumors using steroid metabolomics data, (II) the early diagnosis of rheumatoid arthritis based on cytokine expression and (III) the detection and discrimination of neuro- degenerative diseases in 3D brain images.
Catégories: Data Science Colloquium
Mot-clés : Médecine, image 3D, machine learning, intelligence artificielle
Voir aussi
|
|
University of Groningen
Physicien / Professeur en informatique
Plus sur cet auteur
Voir la fiche de l'auteur
Cursus :
Michael Biehl est professeur en informatique, apprentissage automatique et intelligence informatique.
Cliquer ICI pour fermerDernière mise à jour : 24/06/2020
Tous droits réservés
@ 2011 ENS