English

A global universality of two-layer neural networks with ReLU activations

Machine Learning 2020-11-23 v1 Functional Analysis

Abstract

In the present study, we investigate a universality of neural networks, which concerns a density of the set of two-layer neural networks in a function spaces. There are many works that handle the convergence over compact sets. In the present paper, we consider a global convergence by introducing a norm suitably, so that our results will be uniform over any compact set.

Keywords

Cite

@article{arxiv.2011.10225,
  title  = {A global universality of two-layer neural networks with ReLU activations},
  author = {Naoya Hatano and Masahiro Ikeda and Isao Ishikawa and Yoshihiro Sawano},
  journal= {arXiv preprint arXiv:2011.10225},
  year   = {2020}
}