Towards a Universal Data Training Set for Coded-Diffraction Image Reconstruction and No-Hidden-Layer Neural Networks
Baurzhan Muminov, Altai Perry, Rakib Hyder, Muhammad Salman Asif, Luat T. Vuong · 2021
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.