Back to Search
Start Over
Deep learning via dynamical systems: An approximation perspective.
- Source :
- Journal of the European Mathematical Society (EMS Publishing); 2023, Vol. 25 Issue 5, p1671-1709, 39p
- Publication Year :
- 2023
-
Abstract
- We build on the dynamical systems approach to deep learning, where deep residual networks are idealized as continuous-time dynamical systems, from the approximation perspective. In particular, we establish general sufficient conditions for universal approximation using continuoustime deep residual networks, which can also be understood as approximation theories in Lp using flow maps of dynamical systems. In specific cases, rates of approximation in terms of the time horizon are also established. Overall, these results reveal that composition function approximation through flow maps presents a new paradigm in approximation theory and contributes to building a useful mathematical framework to investigate deep learning. [ABSTRACT FROM AUTHOR]
Details
- Language :
- English
- ISSN :
- 14359855
- Volume :
- 25
- Issue :
- 5
- Database :
- Complementary Index
- Journal :
- Journal of the European Mathematical Society (EMS Publishing)
- Publication Type :
- Academic Journal
- Accession number :
- 163934443
- Full Text :
- https://doi.org/10.4171/JEMS/1221