Computational separation between convolutional and fully-connected networks

E Malach, S Shalev-Shwartz - arXiv preprint arXiv:2010.01369, 2020 - arxiv.org
Convolutional neural networks (CNN) exhibit unmatched performance in a multitude of
computer vision tasks. However, the advantage of using convolutional networks over fully …
Speichern Sie Cite Cited by 19 Related articles View as HTML

Computational Separation Between Convolutional and Fully-Connected Networks

E Malach, S Shalev-Shwartz - arXiv e-prints, 2020 - ui.adsabs.harvard.edu
Convolutional neural networks (CNN) exhibit unmatched performance in a multitude of
computer vision tasks. However, the advantage of using convolutional networks over fully …
Cite