Paper
3 May 1988 Optical Implementation Of Winner-Take-All Networks: Noise Considerations
S M Rovnyak, C W Stirk, R A Athale
Author Affiliations +
Proceedings Volume 0882, Neural Network Models for Optical Computing; (1988) https://doi.org/10.1117/12.944113
Event: 1988 Los Angeles Symposium: O-E/LASE '88, 1988, Los Angeles, CA, United States
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.
© (1988) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
S M Rovnyak, C W Stirk, and R A Athale "Optical Implementation Of Winner-Take-All Networks: Noise Considerations", Proc. SPIE 0882, Neural Network Models for Optical Computing, (3 May 1988); https://doi.org/10.1117/12.944113
Advertisement
Advertisement
RIGHTS & PERMISSIONS
Get copyright permission  Get copyright permission on Copyright Marketplace
KEYWORDS
Neurons

Neural networks

Interference (communication)

Analog electronics

Systems modeling

Optical computing

Tolerancing

RELATED CONTENT


Back to Top