Exponential convergence of the deep neural network approximation for analytic functions

E. Weinan, Qingcan Wang

Research output: Contribution to journalArticlepeer-review

54 Scopus citations

Abstract

We prove that for analytic functions in low dimension, the convergence rate of the deep neural network approximation is exponential.

Original languageEnglish (US)
Pages (from-to)1733-1740
Number of pages8
JournalScience China Mathematics
Volume61
Issue number10
DOIs
StatePublished - Oct 1 2018

All Science Journal Classification (ASJC) codes

  • General Mathematics

Keywords

  • Primary 65D15
  • analytic functions
  • approximation theory
  • neural networks
  • secondary 41-04

Fingerprint

Dive into the research topics of 'Exponential convergence of the deep neural network approximation for analytic functions'. Together they form a unique fingerprint.

Cite this