Zobrazeno 1 - 1
of 1
pro vyhledávání: '"D. J. Romero-Lopez"'
Publikováno v:
Journal of Mathematical Analysis and Applications. 494:124584
We prove a negative result for the approximation of functions defined on compact subsets of $\mathbb{R}^d$ (where $d \geq 2$) using feedforward neural networks with one hidden layer and arbitrary continuous activation function. In a nutshell, this re
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::aade2d38864e6c65a8035451e734caf8
https://doi.org/10.1016/j.jmaa.2020.124584
https://doi.org/10.1016/j.jmaa.2020.124584
