Theoretical Methods of Deep Learning (MA030327)
Deep Learning (DL) is a highly promising and popular applied science that, at present, is poorly understood theoretically. We know that neural networks work well, but cannot fully explain why. Nevertheless, in the last few years, there has been a rapid growth of publications that shed light on the new mathematics underlying DL, and we see now many interesting connections between DL and other fields such as approximation theory, differential equations, information theory, random matrix theory and statistical physics. This course aims to introduce students to these cutting-edge developments.