On sample complexity of neural networks
Machine Learning
2019-10-25 v1 Machine Learning
Abstract
We consider functions defined by deep neural networks as definable objects in an o-miminal expansion of the real field, and derive an almost linear (in the number of weights) bound on sample complexity of such networks.
Keywords
Cite
@article{arxiv.1910.11080,
title = {On sample complexity of neural networks},
author = {Alexander Usvyatsov},
journal= {arXiv preprint arXiv:1910.11080},
year = {2019}
}