Peter Bartlett and Bin Yu to lead $10M NSF/Simons Foundation program to investigate theoretical underpinnings of deep learning

The National Science Foundation (NSF) and the Simons Foundation Division of Mathematics and Physical Sciences are partnering to award $10 million to fund research in the Mathematical and Scientific Foundations of Deep Learning, led by CS Prof. Peter Bartlett and EECS Prof. Bin Yu.  Both professors hold joint appointments in the Department of Statistics.  The researchers hope to gain a better theoretical understanding of deep learning, which is part of a broader family of machine learning methods based on artificial neural networks that digest large amounts of raw data inputs and train AI systems with limited human supervision. Most of the research and education activities will be hosted by the Simons Institute for the Theory of Computing, in the form of structured programs of varying themes.  Other participating institutions will include Stanford, MIT, UCI, UCSD, Toyota Tech in Chicago, EPFL in Switzerland, and the Hebrew University in Israel.