ICS Colloquium: Gaël Varoquaux, Ph.D., McGill University
Title: Functional neuroimaging at scale, a quest for big picture on brain function
Presenter: Research Director, Parietal, National Institute for Research in Computer Science and Control (on sabbatical leave at McGill University)
Abstract: Establishing general findings on mental function is challenging. Individual studies all ask different questions that are not unified to model brain-mind relationships in any given situation. Observed effects may be determined by details of the psychological manipulation. Cohorts recruit a specific population, often singling out a pathology. Most studies suffer from a lack of statistical power.
I will present a research program to address these challenges in brain imaging by using explicit predictive modeling (machine learning) to assemble a coherent picture across a very diverse set of conditions, increasing statistical power and generality of findings. Decoding brain responses across studies maps neural supports of mental processes that generalize across psychological manipulations. Predicting reported brain locations from the full text of a publication can give meta-analyses well suited to the verbal nature of psychological theories. Extracting biomarkers of mental disorders across sites can tame inter-site heterogeneity.
Bio: Gaël Varoquaux is an Inria faculty researcher working on data science and brain imaging. He has a joint position at Inria (French Computer Science National research) and in the Neurospin brain research institute. His research focuses on using data and machine learning for scientific inference, applying it to brain-imaging data to understand cognition, as well as developing tools that make it easier for non-specialists to use machine learning. Years before the NSA, he was hoping to make bleeding-edge data processing available across new fields, and he has been working on a mastermind plan building easy-to-use open-source software in Python. He is a core developer of scikit-learn, joblib, Mayavi and nilearn, a nominated member of the PSF, and often teaches scientific computing with Python using the scipy lecture notes.
Friday, January 24 at 12:00pm to 2:00pm
Muenzinger Psychology, Room D430 on the fourth floor
1905 Colorado Avenue, Boulder, CO 80309