Functional Neuronal Networks

Explore a comprehensive lecture on Functional Neuronal Networks presented by Jiguo Cao as part of the Colloque des sciences mathématiques du Québec (CSMQ). Delve into the growing field of Functional Data Analysis (FDA) and its applications in analyzing curves, images, and multidimensional functions. Discover a novel methodology for integrating functional data into deep neural networks, designed for scalar responses with multiple functional and scalar covariates. Learn about the unique feature of dynamic functional weights that can be visualized during optimization, offering enhanced interpretability of covariate-response relationships compared to conventional neural networks. Examine the model's performance in predicting new data and recovering true underlying relationships between functional covariates and scalar responses, supported by real data applications and simulation studies. Gain insights into the practical applications of this approach in longitudinal studies and brain imaging.