Part of Advances in Neural Information Processing Systems 4 (NIPS 1991)
Dana Anderson, Claus Benkert, Verena Hebler, Ju-Seog Jang, Don Montgomery, Mark Saffman
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.
image features or carrier