Deep learning in light-matter interactions
Review article, 2022

The deep-learning revolution is providing enticing new opportunities to manipulate and harness light at all scales. By building models of light-matter interactions from large experimental or simulated datasets, deep learning has already improved the design of nanophotonic devices and the acquisition and analysis of experimental data, even in situations where the underlying theory is not sufficiently established or too complex to be of practical use. Beyond these early success stories, deep learning also poses several challenges. Most importantly, deep learning works as a black box, making it difficult to understand and interpret its results and reliability, especially when training on incomplete datasets or dealing with data generated by adversarial approaches. Here, after an overview of how deep learning is currently employed in photonics, we discuss the emerging opportunities and challenges, shining light on how deep learning advances photonics.

deep learning

neural networks

optics

photonics

Author

Daniel Midtvedt

University of Gothenburg

Vasilii Mylnikov

Chalmers, Physics, Nano and Biophysics

Alexander Stilgoe

University of Queensland

Mikael Käll

Chalmers, Physics, Nano and Biophysics

Halina Rubinsztein-Dunlop

University of Queensland

Giovanni Volpe

University of Gothenburg

Nanophotonics

21928614 (eISSN)

Vol. 11 14 3189-3214

Subject Categories

Media and Communication Technology

Learning

Information Science

DOI

10.1515/nanoph-2022-0197

More information

Latest update

3/21/2023