– Soutenance de thèse de S. Takerkart (LIF, INT) : A multi-source perspective on inter-subject learning. Contributions to neuroimaging.

Carte non disponible

Date/heure
Date(s) - 24 septembre 2015

Catégories Pas de Catégories


Soutenance de thèse de Sylvain Takerkart\n\nA multi-source perspective on inter-subject learning. Contributions to neuroimaging.\n\nSalle Henri Gastaut\nCampus santé Timone\n27, boulevard Jean Moulin\n13385 Marseille cedex 5\n\nJury :\nPr. Rainer Goebel (Maastricht University, The Netherlands), rapporteur\nPr. Patrick Gallinari (Université Pierre et Marie Curie, Paris), rapporteur\nDr. Jean-François Mangin (CEA, Saclay), examinateur\nDr. Bertrand Thirion (INRIA, Saclay), examinateur\nDr. Olivier Coulon (CNRS, Marseille), co-directeur de thèse\nPr. Liva Ralaivola (Aix-Marseille Université, Marseille), directeur de thèse\n\nAbstract :\n\nInter-subject learning consists in giving predictions on data from a subject not present in the training database, as with computer-aided diagnosis where the computer has to guess wether an unknown individual is healthy or sick. In this thesis, we argue that inter-subject learning should be handled in the multi-source framework where each subject is a different source of data. We then introduce three original contributions for neuroimaging applications.\n\nThe first one is a method for inter-subject predictions of fMRI data. Because of the inter-subject variability, the original feature spaces are all different. Using graphs and a graph kernel, the input patterns are implicitly projected into a common reproducing kernel hilbert space. We show the effectiveness of this method on tonotopy data recorded in the auditory cortex.\n\nThe second one is a cortical morphometry method. We design graphs from the deepest points of cortical sulci, and we project them into a common space using a graph kernel. A spatial inference method is then proposed to perform the detection of cortical zones where populations are different. Using this method, we study cortical asymmetries and gender differences.\n\nThe third contribution of this thesis is a multi-source domain adaptation technique. Our method is an extension of the kernel mean matching for the multi-source case. We present preliminary results on a inter-subject prediction task used to analyse data from a magneto-encephalography experiment.[

– Soutenance de thèse de S. Takerkart (LIF, INT) : A multi-source perspective on inter-subject learning. Contributions to neuroimaging.

Carte non disponible

Date/heure
Date(s) - 24 septembre 2015

Catégories Pas de Catégories


Soutenance de thèse de Sylvain Takerkart\n\nA multi-source perspective on inter-subject learning. Contributions to neuroimaging.\n\nSalle Henri Gastaut\nCampus santé Timone\n27, boulevard Jean Moulin\n13385 Marseille cedex 5\n\nJury :\nPr. Rainer Goebel (Maastricht University, The Netherlands), rapporteur\nPr. Patrick Gallinari (Université Pierre et Marie Curie, Paris), rapporteur\nDr. Jean-François Mangin (CEA, Saclay), examinateur\nDr. Bertrand Thirion (INRIA, Saclay), examinateur\nDr. Olivier Coulon (CNRS, Marseille), co-directeur de thèse\nPr. Liva Ralaivola (Aix-Marseille Université, Marseille), directeur de thèse\n\nAbstract :\n\nInter-subject learning consists in giving predictions on data from a subject not present in the training database, as with computer-aided diagnosis where the computer has to guess wether an unknown individual is healthy or sick. In this thesis, we argue that inter-subject learning should be handled in the multi-source framework where each subject is a different source of data. We then introduce three original contributions for neuroimaging applications.\n\nThe first one is a method for inter-subject predictions of fMRI data. Because of the inter-subject variability, the original feature spaces are all different. Using graphs and a graph kernel, the input patterns are implicitly projected into a common reproducing kernel hilbert space. We show the effectiveness of this method on tonotopy data recorded in the auditory cortex.\n\nThe second one is a cortical morphometry method. We design graphs from the deepest points of cortical sulci, and we project them into a common space using a graph kernel. A spatial inference method is then proposed to perform the detection of cortical zones where populations are different. Using this method, we study cortical asymmetries and gender differences.\n\nThe third contribution of this thesis is a multi-source domain adaptation technique. Our method is an extension of the kernel mean matching for the multi-source case. We present preliminary results on a inter-subject prediction task used to analyse data from a magneto-encephalography experiment.[