Network Generalization for Production: Learning and Producing Styled Letterforms
Abstract
We designed and trained a connectionist network to generate letterfonns in a new font given just a few exemplars from that font. During learning. our network constructed a distributed internal representation of fonts as well as letters. despite the fact that each training instance exemplified both a font and a letter. It was necessary to have separate but interconnected hidden units for " letter" and "font" representations - several alternative architectures were not successful.
Cite
Text
Grebert et al. "Network Generalization for Production: Learning and Producing Styled Letterforms." Neural Information Processing Systems, 1991.Markdown
[Grebert et al. "Network Generalization for Production: Learning and Producing Styled Letterforms." Neural Information Processing Systems, 1991.](https://mlanthology.org/neurips/1991/grebert1991neurips-network/)BibTeX
@inproceedings{grebert1991neurips-network,
title = {{Network Generalization for Production: Learning and Producing Styled Letterforms}},
author = {Grebert, Igor and Stork, David G. and Keesing, Ron and Mims, Steve},
booktitle = {Neural Information Processing Systems},
year = {1991},
pages = {1118-1124},
url = {https://mlanthology.org/neurips/1991/grebert1991neurips-network/}
}