An introduction to the mathematics of deep learning (Q6064555)
From MaRDI portal
scientific article; zbMATH DE number 7763386
Language | Label | Description | Also known as |
---|---|---|---|
English | An introduction to the mathematics of deep learning |
scientific article; zbMATH DE number 7763386 |
Statements
An introduction to the mathematics of deep learning (English)
0 references
10 November 2023
0 references
Summary: 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. For the entire collection see [Zbl 1519.00033].
0 references
approximation theory
0 references
deep learning
0 references
inverse problems
0 references
parametric partial differential equations
0 references
0 references
0 references
0 references