Conditional recurrent neural networks for broad applications in nonlinear optics

Simone Lauria, Mohammed F. Saleh

Research output: Contribution to journalArticlepeer-review

17 Downloads (Pure)

Abstract

We present a novel implementation of conditional long short-term memory recurrent neural networks that successfully predict the spectral evolution of a pulse in nonlinear periodically-poled waveguides. The developed networks offer large flexibility by allowing the propagation of optical pulses with ranges of energies and temporal widths in waveguides with different poling periods. The results show very high agreement with the traditional numerical models. Moreover, we are able to use a single network to calculate both the real and imaginary parts of the pulse complex envelope, allowing for successfully retrieving the pulse temporal and spectral evolution using the same network.
Original languageEnglish
Pages (from-to)5582-5591
Number of pages10
JournalOptics Express
Volume32
Issue number4
Early online date1 Feb 2024
DOIs
Publication statusPublished - 12 Feb 2024

Fingerprint

Dive into the research topics of 'Conditional recurrent neural networks for broad applications in nonlinear optics'. Together they form a unique fingerprint.

Cite this