In this paper, we present Neural Glyph, a system that generates novel glyph without any training data. The generator and the classifier are trained to communicate via visual symbols as a medium, which enforces the generator to come up with a set of distinctive symbols. Our method results in glyphs that resemble the human-made glyphs, which may imply that the visual appearances of existing glyphs can be attributed to constraints of communication via writing. Important tricks that enable this framework are described and the code is made available.
Cite
@article{arxiv.2010.04402,
title = {Generating Novel Glyph without Human Data by Learning to Communicate},
author = {Seung-won Park},
journal= {arXiv preprint arXiv:2010.04402},
year = {2020}
}
Comments
To appear at 4th Workshop on Machine Learning for Creativity and Design at NeurIPS 2020; 6 pages with 4 figures and 1 table