This project aims to develop novel statistical machine learning methods for big neuroimaging data.
The scientific goal is to investigate at a large scale how changes in connectivity and activation are driven by task challenges and how multiple brain pathways process stimulus information. The methodological goal is to develop fundamental learning theory about inferring large dynamic graphs with trillions of connections. The computational goal is to develop practical tools for modeling terabytes of data. This project will also perform comprehensive validation and assessment of the newly developed methods, and provide open source software implementations for a broad range of use in the scientific community.