An introduction to the mathematics of deep learning
Gitta Kutyniok
Ludwig-Maximilians-Universität München; and Munich Center for Machine Learning, Germany; University of Tromsø - The Arctic University of Norway, Norway
This book chapter is published open access.
Abstract
Despite the outstanding success of deep neural networks in real-world applications, ranging from science to public life, most of the related research is empirically driven and a comprehensive mathematical foundation is still missing. At the same time, these methods have already shown their impressive potential in mathematical research areas such as imaging sciences, inverse problems, or numerical analysis of partial differential equations, sometimes by far outperforming classical mathematical approaches for particular problem classes.
The goal of this paper, which is based on a plenary lecture at the 8th European Congress of Mathematics in 2021, is to first provide an introduction into this new vibrant research area. We will then showcase some recent advances in two directions, namely the development of a mathematical foundation of deep learning and the introduction of novel deep learning-based approaches to solve inverse problems and partial differential equations.