arXiv Analytics

Sign in

arXiv:1810.10032 [cs.LG]AbstractReferencesReviewsResources

Some negative results for Neural Networks

J. M. Almira, P. E. Lopez-de-Teruel, D. J. Romero-Lopez

Published 2018-10-23Version 1

We demonstrate some negative results for approximation of functions with neural networks.

Comments: 11 pages, submitted to a Journal
Categories: cs.LG, stat.ML
Related articles: Most relevant | Search more
arXiv:1805.09370 [cs.LG] (Published 2018-05-23)
Towards Robust Training of Neural Networks by Regularizing Adversarial Gradients
arXiv:1706.02690 [cs.LG] (Published 2017-06-08)
Principled Detection of Out-of-Distribution Examples in Neural Networks
arXiv:1904.01399 [cs.LG] (Published 2019-04-02)
On Geometric Structure of Activation Spaces in Neural Networks

Links

Toolbox