Presentation
1 August 2021 Optical computing with multimode fiber nonlinearities
Ugur Tegin, Mustafa Yildirim, Ilker Oguz, Christophe Moser, Demetri Psaltis
Author Affiliations +
Abstract
A novel optical computing framework is presented by harnessing spatiotemporal nonlinear effects of multimode fibers for machine learning. With linear and nonlinear interactions of spatial fiber modes, a powerful computation engine is experimentally realized. We demonstrated excellent performance with the present optical scheme for various classification tasks. We demonstrated that spatiotemporal fiber nonlinearities perform as well as digital neural network structures for challenging computational tasks. With better energy efficiency and easy scalability, our method presents a novel path toward powerful optical computation.
Conference Presentation
© (2021) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Ugur Tegin, Mustafa Yildirim, Ilker Oguz, Christophe Moser, and Demetri Psaltis "Optical computing with multimode fiber nonlinearities", Proc. SPIE 11804, Emerging Topics in Artificial Intelligence (ETAI) 2021, 118040F (1 August 2021); https://doi.org/10.1117/12.2594821
Advertisement
Advertisement
KEYWORDS
Multimode fibers

Nonlinear optics

Optical computing

Neural networks

Optical signal processing

Picosecond phenomena

Structured optical fibers

RELATED CONTENT

Nonlinear spatiotemporal optical computing
Proceedings of SPIE (January 01 1900)
Laser plasma diagnostics of dense plasmas
Proceedings of SPIE (September 18 1995)
Optical Computing With Nonlinear Optics
Proceedings of SPIE (January 01 1987)
Scalable nonlinear optical computing with multimode fibers
Proceedings of SPIE (January 01 1900)

Back to Top