Share Email Print

Proceedings Paper

A Class of Continuous Level Neural Nets
Author(s): Robert J. Marks; Les E. Atlas; Kwan F. Cheung
Format Member Price Non-Member Price
PDF $14.40 $18.00

Paper Abstract

A neural net capable of restoring continuous level library vectors from memory is considered. The vectors in the memory library are used to program the neural interconnects. Given a portion of one of the library vectors, the net extrapolates the remainder. Sufficient conditions for unique convergence are stated. An architecture for optical implementation of the network is proposed.

Paper Details

Date Published: 1 January 1987
PDF: 2 pages
Proc. SPIE 0813, Optics and the Information Age, (1 January 1987); doi: 10.1117/12.967138
Show Author Affiliations
Robert J. Marks, University of Washington (United States)
Les E. Atlas, University of Washington (United States)
Kwan F. Cheung, University of Washington (United States)

Published in SPIE Proceedings Vol. 0813:
Optics and the Information Age
Henri H. Arsenault, Editor(s)

© SPIE. Terms of Use
Back to Top