Journal
OPTICS EXPRESS
Volume 27, Issue 10, Pages 14009-14029Publisher
OPTICAL SOC AMER
DOI: 10.1364/OE.27.014009
Keywords
-
Categories
Funding
- U.S. Army Research Laboratory
- U.S. Army Research Office [W911NF-13-1-0390]
Ask authors/readers for more resources
For the benefit of designing scalable, fault resistant optical neural networks (ONNs), we investigate the effects architectural designs have on the ONNs' robustness to imprecise components. We train two ONNs - one with a more tunable design (GridNet) and one with better fault tolerance (FFTNet) - to classify handwritten digits. When simulated without any imperfections, GridNet yields a better accuracy (similar to 98%) than FFTNet (similar to 95%). However, under a small amount of error in their photonic components, the more fault tolerant FFTNet overtakes GridNet. We further provide thorough quantitative and qualitative analyses of ONNs' sensitivity to varying levels and types of imprecisions. Our results offer guidelines for the principled design of fault-tolerant ONNs as well as a foundation for further research. (C) 2019 Optical Society of America under the terms of the OSA Open Access Publishing Agreement
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available