Optical Implementation of a Self-Organizing Feature Extractor
Abstract
We demonstrate a self-organizing system based on photorefrac(cid:173) tive ring oscillators. We employ the system in two ways that can both be thought of as feature extractors; one acts on a set of images exposed repeatedly to the system strictly as a linear feature extractor, and the other serves as a signal demultiplex(cid:173) er for fiber optic communications. Both systems implement unsupervised competitive learning embedded within the mode interaction dynamics between the modes of a set of ring oscilla(cid:173) tors. After a training period, the modes of the rings become as(cid:173) sociated with frequencies within the incoming data stream.
Cite
Text
Anderson et al. "Optical Implementation of a Self-Organizing Feature Extractor." Neural Information Processing Systems, 1991.Markdown
[Anderson et al. "Optical Implementation of a Self-Organizing Feature Extractor." Neural Information Processing Systems, 1991.](https://mlanthology.org/neurips/1991/anderson1991neurips-optical/)BibTeX
@inproceedings{anderson1991neurips-optical,
title = {{Optical Implementation of a Self-Organizing Feature Extractor}},
author = {Anderson, Dana Z. and Benkert, Claus and Hebler, Verena and Jang, Ju-Seog and Montgomery, Don and Saffman, Mark},
booktitle = {Neural Information Processing Systems},
year = {1991},
pages = {821-828},
url = {https://mlanthology.org/neurips/1991/anderson1991neurips-optical/}
}