Human Reading and the Curse of Dimensionality
Abstract
Whereas optical character recognition (OCR) systems learn to clas(cid:173) sify single characters; people learn to classify long character strings in parallel, within a single fixation . This difference is surprising because high dimensionality is associated with poor classification learning. This paper suggests that the human reading system avoids these problems because the number of to-be-classified im(cid:173) ages is reduced by consistent and optimal eye fixation positions, and by character sequence regularities.
Cite
Text
Martin. "Human Reading and the Curse of Dimensionality." Neural Information Processing Systems, 1995.Markdown
[Martin. "Human Reading and the Curse of Dimensionality." Neural Information Processing Systems, 1995.](https://mlanthology.org/neurips/1995/martin1995neurips-human/)BibTeX
@inproceedings{martin1995neurips-human,
title = {{Human Reading and the Curse of Dimensionality}},
author = {Martin, Gale},
booktitle = {Neural Information Processing Systems},
year = {1995},
pages = {17-23},
url = {https://mlanthology.org/neurips/1995/martin1995neurips-human/}
}