The Collaboration on the Theoretical Foundations of Deep Learning is a team of eleven research leaders from eight institutions around the world, sponsored by NSF and Simons Foundation, with the aim of addressing theoretical challenges of deep learning, extending its applicability, and developing new methods.
The National Science Foundation and the Simons Foundation Division of Mathematics and Physical Sciences have partnered to fund research in the mathematical and scientific foundations of deep learning.
The Collaboration on the Theoretical Foundations of Deep Learning aims to understand the mathematical mechanisms that underpin the practical success of deep learning, use this understanding to elucidate the limitations of current methods and extend them beyond the domains where they are currently applicable, and initiate the study of the mathematical problems that emerge.