Towards Training Fault Tolerant and Noise Immune Diffractive Optical Neural Engines
Author(s)
S.S., Panda, Soumyashree Soumyaprakash
Abstract
We report a novel robust training regimen for Diffractive Optical Networks that uses gradient based regularization terms in the training objective. Enhanced fault tolerance and noise immunity has been observed with models trained with this method. � 2021 Elsevier B.V., All rights reserved.
Keywords
Optical fiber communication
Optical fibers
Fault-tolerant
Gradient based
Noise immune
Noise immunity
Optical-
Regularization terms
Robust trainings
Fault tolerance