We prove that for analytic functions in low dimension, the convergence rate of the deep neural network approximation is exponential.
All Science Journal Classification (ASJC) codes
- Primary 65D15
- analytic functions
- approximation theory
- neural networks
- secondary 41-04
Weinan, E., & Wang, Q. (2018). Exponential convergence of the deep neural network approximation for analytic functions. Science China Mathematics, 61(10), 1733-1740. https://doi.org/10.1007/s11425-018-9387-x