Morten Mørup March 24 at 10

On Monday, March 24 @ 10:00 at the Biostat Library:

Morten Mørup, Danish Technical University

"Characterizing Neural Responses, Individual Variability, and the Functional and Structural Organization of Connectomes using Machine Learning"

This talk will describe our research efforts towards using machine learning to extract patterns and account for individual variability in functional neuroimaging data. A primer will be given to machine learning and the importance of model generalization as well as how (non-parametric) Bayesian inference and predictive assessments can be used to evidence plausible hypothesis of brain organization. The talk will further highlight efforts towards characterizing individual variability in neural responses by use of deep learning voice conversion technologies adapted to the functional neuroimaging domain. Finally it will be discussed how machine learning can potentially be used to reduce the number of trials necessary in functional neuroimaging research.