Share Email Print

Proceedings Paper

Optical Implementation Of Winner-Take-All Networks: Noise Considerations
Author(s): S M Rovnyak; C W Stirk; R A Athale
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

Variation in the response of hardware components causes analog implementations of neural networks with soft nonlinearities to corrupt their signals with noise. In this paper we simulate the behavior of analog implementations of multiplicative and additive winner-take-all lateral-inhibitory-networks (WTA-LIN) for different levels of component variation. We observe that for an acceptable level of performance the amplitude resolution and number of the initial neuron activities are constrained by the standard deviation of the component nonuniformity.

Paper Details

Date Published: 3 May 1988
PDF: 6 pages
Proc. SPIE 0882, Neural Network Models for Optical Computing, (3 May 1988); doi: 10.1117/12.944113
Show Author Affiliations
S M Rovnyak, The BDM Corporation (United States)
C W Stirk, The BDM Corporation (United States)
R A Athale, The BDM Corporation (United States)

Published in SPIE Proceedings Vol. 0882:
Neural Network Models for Optical Computing
Ravindra A. Athale; Joel Davis, Editor(s)

© SPIE. Terms of Use
Back to Top