Photodetector Performance Prediction with Machine Learning

Thumbnail Image

Files

fio2021ftu6c.4.pdf (892.63 KB)

Links to Files

https://opg.optica.org/abstract.cfm?uri=FiO-2021-FTu6C.4

Permanent Link

https://doi.org/10.1364/FIO.2021.FTu6C.4
 http://hdl.handle.net/11603/38991

Collections

UMBC Student Collection
UMBC Computer Science and Electrical Engineering Department
UMBC Data Science
UMBC Faculty Collection

Author/Creator

Author/Creator ORCID

https://orcid.org/0000-0001-9075-7071
 https://orcid.org/0000-0003-4718-6976
 https://orcid.org/0000-0002-5002-1657
 https://orcid.org/0000-0003-0269-8433

Date

2021-11-01

Type of Work

conference papers and proceedings
Text

Department

Program

Citation of Original Publication

Simsek, Ergun, Seyed Ehsan Jamali Mahabadi, Thomas F. Carruthers, and Curtis R. Menyuk. "Photodetector Performance Prediction with Machine Learning" In Frontiers in Optics + Laser Science 2021 (2021), Paper FTu6C.4, FTu6C.4. Optica Publishing Group, 2021. https://doi.org/10.1364/FIO.2021.FTu6C.4.

Rights

This item is likely protected under Title 17 of the U.S. Copyright Law. Unless on a Creative Commons license, for uses protected by Copyright Law, contact the copyright holder or the author.

Subjects

Neural networks
UMBC Optical Fiber Communications Laboratory
UMBC High Performance Computing Facility (HPCF)
Phase noise
UMBC Computational Photonics Laboratory
Ultrashort pulses
Distortion
Photodetectors
Machine learning

Abstract

Four machine learning algorithms are tested to predict the performance metrics of modified uni-traveling carrier photodetectors from their design parameters. The highest accuracy (>94%) is achieved with artificial neural networks.