An Empirical Study of the Relation Between Network Architecture and Complexity
Abstract
In this preregistration submission, we propose an empirical study of how networks handle changes in complexity of the data. We investigate the effect of network capacity on generalization performance in the face of increasing data complexity. For this, we measure the generalization error for an image classification task where the number of classes steadily increases. We compare a number of modern architectures at different scales in this setting. The methodology, setup, and hypotheses described in this proposal were evaluated by peer review before experiments were conducted.
Cite
Text
Konuk and Smith. "An Empirical Study of the Relation Between Network Architecture and Complexity." IEEE/CVF International Conference on Computer Vision Workshops, 2019. doi:10.1109/ICCVW.2019.00563Markdown
[Konuk and Smith. "An Empirical Study of the Relation Between Network Architecture and Complexity." IEEE/CVF International Conference on Computer Vision Workshops, 2019.](https://mlanthology.org/iccvw/2019/konuk2019iccvw-empirical/) doi:10.1109/ICCVW.2019.00563BibTeX
@inproceedings{konuk2019iccvw-empirical,
title = {{An Empirical Study of the Relation Between Network Architecture and Complexity}},
author = {Konuk, Emir and Smith, Kevin},
booktitle = {IEEE/CVF International Conference on Computer Vision Workshops},
year = {2019},
pages = {4597-4599},
doi = {10.1109/ICCVW.2019.00563},
url = {https://mlanthology.org/iccvw/2019/konuk2019iccvw-empirical/}
}