Network Neuroscience in the Age of AI

Network Neuroscience is a recently developed field of neuroscience that draws upon tools from network theory to understand how brain network structure drives brain function.  Experimental neuroimaging data is first mapped to a brain network, and the resulting network structure is quantified using network statistics.  In this talk, I will present some previous work that developed novel dynamic community detection methods (unsupervised machine learning algorithms) to better capture the unique statistical properties of brain network data and show how the application of these algorithms can help answer pertinent biological questions in the context of epilepsy research.  I will then discuss some current and future work that will leverage AI to reveal specific network features and circuitry involved in decision making processes.  Finally, I will discuss how network-based approaches and lessons learned from observations of brain structure can be used to guide decisions in the future development of AI architectures across a multitude of applications.

Dr. Sarah Muldoon is an Associate Professor in the Mathematics Department, Director of the PhD Program in Computational and Data-Enabled Sciences through the Institute for Artificial Intelligence and Data Science, member of the Center for Cognitive Science, and member of the Neuroscience Program at the University at Buffalo, SUNY.  Her research interests lie at the intersection of experiment and theory with a focus on applications of network theory to neuroscience data. She has spent extensive time working in experimental neurobiology labs and now runs a research group that couples theoretical advancement, computational modeling, and data-intensive analysis to study the relationship between structure and function in brain networks.