Function approximation by deep neural networks with parameters $\{0,\pm \frac{1}{2}, \pm 1, 2\}$
Machine Learning
2021-07-26 v3 Machine Learning
Abstract
In this paper it is shown that -smooth functions can be approximated by deep neural networks with ReLU activation function and with parameters . The and parameter norms of considered networks are thus equivalent. The depth, width and the number of active parameters of the constructed networks have, up to a logarithmic factor, the same dependence on the approximation error as the networks with parameters in . In particular, this means that the nonparametric regression estimation with the constructed networks attains the same convergence rate as with sparse networks with parameters in .
Cite
@article{arxiv.2103.08659,
title = {Function approximation by deep neural networks with parameters $\{0,\pm \frac{1}{2}, \pm 1, 2\}$},
author = {Aleksandr Beknazaryan},
journal= {arXiv preprint arXiv:2103.08659},
year = {2021}
}