Quantifying the universal approximation theorem

Cross Validated Asked by ofow on January 3, 2022

Let $mgeq 1$ be an integer and $Fin mathbb{R}[x_1, dots, x_m]$ be a polynomial. I want to approximate $F$ on the unit hypercube $[0, 1]^m$ by a (possibly multilayer) feedforward neural network. The activation function is $mathrm{tanh}$ for all the connections.

Let $varepsilon>0$ be a real number. If I want the approximation to deviate from $F$ by less than $varepsilon$ in the $L^2$ norm what is the smallest possible number of non-zero weights?

It is kind of stupid to approximate a function that is known to be polynomial by a neural network but I just wanted to get more quantitative insight into the universal approximation theorem (and polynomials seem to be the most accessible class of functions).

Add your own answers!

Related Questions

report output GLMER and do contrasts

0  Asked on November 24, 2021 by chiara-toschi


Ask a Question

Get help from others!

© 2023 All rights reserved. Sites we Love: PCI Database, UKBizDB, Menu Kuliner, Sharing RPP