Semi-Supervised Factored Logistic Regression for High-Dimensional Neuroimaging Data

Danilo Bzdok (1, 2) , Michael Eickenberg (2, 1) , Olivier Grisel (2, 1) , Bertrand Thirion (2, 1) , Gaël Varoquaux (2, 1)

1 UNATI - Unité Analyse et Traitement de l'Information
2 PARIETAL - Modelling brain structure, function and variability based on high-field MRI data

Imaging neuroscience links human behavior to aspects of brain biology in ever-increasing datasets. Existing neuroimaging methods typically perform either discovery of unknown neural structure or testing of neural structure associated with mental tasks. However, testing hypotheses on the neural correlates underlying larger sets of mental tasks necessitates adequate representations for the observations. We therefore propose to blend representation modelling and task classification into a unified statistical learning problem. A multinomial logistic regression is introduced that is constrained by factored coefficients and coupled with an au-toencoder. We show that this approach yields more accurate and interpretable neural models of psychological tasks in a reference dataset, as well as better generalization to other datasets.

Mots clés: Semi-Supervised Learning; Systems Biology; Brain Imaging; Cognitive Science

Domaines: Bio-informatique [q-bio.QM]; Psychologie; Statistiques [stat]; Machine Learning [stat.ML]

Danilo Bzdok, Michael Eickenberg, Olivier Grisel, Bertrand Thirion, Gaël Varoquaux. Semi-Supervised Factored Logistic Regression for High-Dimensional Neuroimaging Data. NIPS'15: 28th International Conference on Neural Information Processing Systems, Dec 2015, Montreal, Canada. ⟨hal-01211248⟩