Morten Mørup
Professor of machine learning, Section for Cognitive Systems, DTU Compute, Technical University of Denmark
“Modeling Functional Neuroimaging Data using Machine Learning”
Abstract: In this talk I will introduce several unsupervised learning approaches for the characterization of non-invasive functional neuroimaging data based on electro- and magneto-encephalograhy (EEG/MEG) as well as fMRI. In particular, the talk will cover how machine learning can be used to learn from these data the human brain’s functional organization as well as prominent patterns of task induced neural activations while at the same time accounting for individual variability.