On the Universality of Neural Codes in Vision
Abstract
A high level of similarity between neural codes of natural images has been reported for both biological and artificial brains. These observations beg the question whether this similarity of representations stems from a more fundamental similarity between neural coding strategies. In this paper, we show that neural networks trained on different image classification datasets learn similar weight summary statistics. Our results reveal the existence of a universal neural code for natural images.
Cite
Text
Guth and Ménard. "On the Universality of Neural Codes in Vision." NeurIPS 2023 Workshops: UniReps, 2023.Markdown
[Guth and Ménard. "On the Universality of Neural Codes in Vision." NeurIPS 2023 Workshops: UniReps, 2023.](https://mlanthology.org/neuripsw/2023/guth2023neuripsw-universality/)BibTeX
@inproceedings{guth2023neuripsw-universality,
title = {{On the Universality of Neural Codes in Vision}},
author = {Guth, Florentin and Ménard, Brice},
booktitle = {NeurIPS 2023 Workshops: UniReps},
year = {2023},
url = {https://mlanthology.org/neuripsw/2023/guth2023neuripsw-universality/}
}