Abstract
We use a multilayer, nonlinear optical neural network (ONN) as a pre-processor for machine vision. On tasks including identification of real objects illuminated by broadband incoherent light, we show that nonlinear optical pre-processing outperforms linear pre-processing.
© 2023 The Author(s)
PDF Article | Presentation VideoMore Like This
Mandar M. Sohoni, Tianyu Wang, Logan G. Wright, Martin M. Stein, Shi-Yuan Ma, Tatsuhiro Onodera, Maxwell G. Anderson, and Peter L. McMahon
STu4F.3 CLEO: Science and Innovations (CLEO:S&I) 2023
Mandar M. Sohoni, Tianyu Wang, Logan G. Wright, Tatsuhiro Onodera, Martin M. Stein, Shi-Yuan Ma, Maxwell Anderson, and Peter L. McMahon
JTu2A.43 Bragg Gratings, Photosensitivity and Poling in Glass Waveguides and Materials (BGPP) 2022
Ilker Oguz, Louis J. E. Suter, Jih-Liang Hsieh, Mustafa Yildirim, Niyazi Ulas Dinc, Christophe Moser, and Demetri Psaltis
Tu3B.5 Nonlinear Optics (NLO) 2023