The success of deep learning has had a major impact across industry, commerce, science and society. But there are many aspects of this technology that are very different from classical methodology and that are poorly understood. A theoretical understanding will be crucial for overcoming its drawbacks.
The Collaboration on the Theoretical Foundations of Deep Learning aims to address these challenges: understanding the mathematical mechanisms that underpin the practical success of deep learning, using this understanding to elucidate the limitations of current methods and extending them beyond the domains where they are currently applicable, and initiating the study of the array of mathematical problems that emerge. The collaboration is jointly funded by the National Science Foundation and the Simons Foundation. It involves 11 PIs from 8 institutions, features postdoc and visit programs, and aims for broad and diverse participation in its activities. Many of the collaboration's activities will be hosted at the Simons Institute for the Theory of Computing at UC Berkeley, including a summer school and workshops on theoretical topics in deep learning.
For more information, email firstname.lastname@example.org.