The goal of this graduate-level course is to describe the mathematical aspects of the incipient theory of Deep Learning, with an emphasis on open questions and intended for graduate students aiming to focus on theoretical aspects of DL.
The course is divided in two parts: (i) Geometric Deep Learning Theory, focusing on the geometry of the input domain arising from the physical world (grids, 3d, graphs); and (ii) Foundations of Deep Learning, covering the foundations of approximation and optimization for Deep Nets.
Lecture Instructor:
TA: