Photonics Research Feature Announcement
Deep Learning in Photonics
Submission Open: 1 October 2020
Submission Deadline: 1 December 2020
The connection between Maxwell's equations and neural network opens exciting opportunities at the interface between photonics and machine learning. This feature issue of Photonics Research will highlight recent research progress at the intersection of photonics and machine learning and provide an opportunity for different communities to exchange cross-field ideas.
The tool of machine learning may revolutionize our capability for photonic design, and our understandings of complex photonic structures. Using neural networks for photonic design allows researchers to tap into a rich set of machine-learning algorithms, such as autoencoder, generative adversarial networks, attention models, transformer models, transfer learning, etc. which may enable highly efficient inverse photonic design.
Machine learning could also help to deepen our understanding of complex nanophotonic structures that derive their properties from a large network of inter-dependent nano-elements with both local and global connections. The vast parameter space offers unprecedented opportunities for device application, but at the same time presents a daunting challenge for developing an understanding of such complex structures.
Integrated photonics could provide a new way to advance computing in machine learning. The ever-increasing computing power required by digital neural networks prompted an effort to search for alternative computing methods that are faster and more energy-efficient. Optical analog computing can be passive with minimal energy consumption, and more importantly, its intrinsic parallelism can significantly accelerate computing speed. Nanostructured photonic devices can exploit sub-wavelength linear and nonlinear scatterers to realize complex input-output mapping far beyond the capabilities of traditional nanophotonic devices. Sophisticated vision tasks can be accomplished passively within the optical domain.
Topics to be covered include, but are not limited to:
- Inverse design by machine learning
- Free space optical neural networks
- Integrated photonics for artificial neural computing
- Photonic neuromorphic computing
- Optical preprocessing for computer vision
- Application of deep learning in sensing and imaging
- Novel concepts and applications of machine learning in photonics
All papers need to present original, previously unpublished work and will be subject to the normal standards and peer review processes of the journal. The standard Photonics Research Article Processing Charges will apply to all published articles.
Please prepare manuscripts according to the author instructions for submission to Photonics Research and submit through OSA's electronic submission system, specifying from the drop-down menu that the manuscript is for the Feature Issue on Deep Learning in Photonics.
Feature Issue Editors
Zongfu Yu, University of Wisconsin, Madison, USA (Lead Editor)
Yang Chai, The Hong Kong Polytechnic University, China
Li Gao, Nanjing University of Posts and Telecommunications, China
Darko Zibar, Technical University of Denmark, Denmark