Convolutional Neural Networks with Fixed Weights

Tyler C. Folsom

2021

Abstract

Improved computational power has enabled artificial neural networks to achieve great success through deep learning. However, visual classification is brittle; networks can be easily confused when a small amount of noise is added to an image. This position paper raises the hypothesis that using all the pixels of an image is wasteful of resources and unstable. Biological neural networks achieve greater success, and the outline of their architecture is well understood and reviewed in this paper. It would behove deep learning network architectures to take additional inspiration from biology to reduce the dimensionality of images and video. Pixels strike the retina, but are convolved before they get to the brain. It has been demonstrated that a set of five filters retains key visual information while achieving compression by an order of magnitude. This paper presents those filters. We propose that images should be pre-processed with a fixed weight convolution that mimics the filtering performed in the retina and primary visual cortex. Deep learning would then be applied to the smaller filtered image.

Download


Paper Citation


in Harvard Style

Folsom T. (2021). Convolutional Neural Networks with Fixed Weights. In Proceedings of the 16th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2021) - Volume 5: VISAPP; ISBN 978-989-758-488-6, SciTePress, pages 516-523. DOI: 10.5220/0010286805160523


in Bibtex Style

@conference{visapp21,
author={Tyler C. Folsom},
title={Convolutional Neural Networks with Fixed Weights},
booktitle={Proceedings of the 16th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2021) - Volume 5: VISAPP},
year={2021},
pages={516-523},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0010286805160523},
isbn={978-989-758-488-6},
}


in EndNote Style

TY - CONF

JO - Proceedings of the 16th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2021) - Volume 5: VISAPP
TI - Convolutional Neural Networks with Fixed Weights
SN - 978-989-758-488-6
AU - Folsom T.
PY - 2021
SP - 516
EP - 523
DO - 10.5220/0010286805160523
PB - SciTePress