Abstract
The stability of an inverse-problem solver depends on algorithm computational complexity. We demonstrate generalizable image reconstruction with the simplest of hybrid machine vision systems: fixed, linear optical preprocessors combined with no-hidden-layer,”small-brain” neural networks.
© 2021 The Author(s)
PDF ArticleMore Like This
Dennis J. Lee, John Mulcahy-Stanislawczyk, Edward Jimenez, Derek West, Ryan Goodner, and Collin Epstein
DF4F.2 Digital Holography and Three-Dimensional Imaging (DH) 2021
Soumyashree S. Panda and Ravi S. Hegde
JW1A.97 CLEO: Applications and Technology (CLEO:A&T) 2021
Luat T. Vuong
FTh4A.3 Frontiers in Optics (FiO) 2021