• Technical Conference:  23 – 26 September 2024
  • Science + Industry Showcase:   24 – 25 September 2024
  • Colorado Convention Center, Denver, Colorado, USA
Home > ePosters > Poster


Referenceless Characterisation of Complex Media Using Physics-Informed Neural Networks (JM4A.43)

Presenter: Suraj Goel, Heriot-Watt University

We accurately characterize the transmission matrices of complex scattering media using a physics-informed, multi-plane neural network (MPNN) without a known reference field. Our method is extremely noise-robust and can characterize a cascade of transmission matrices.

Authors:Suraj Goel, Heriot-Watt University / Claudio Conti, University Sapienza / Saroch Leedumrongwatthanakun, Heriot-Watt University / Mehul Malik, Heriot-Watt University

Poster Presentation

Authentication Required

Access to poster content is available to logged in registered attendees, please login now to participate.