Photonic neural network nonlinear activation functions by electrooptic absorption modulators

Jonathan George, Amin Mehrabian, Rubab Amin, Tarek El-Ghazawi, Paul K. Prucnal, Volker J. Sorger

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

We report on using the transfer function of electrooptic absorption modulators as nonlinear activation functions of photonic neurons and show 95% accuracy of MNIST classification inference on an AlexNet in optical artificial neural networks.

Original languageEnglish (US)
Title of host publicationFrontiers in Optics, FIO 2018
PublisherOSA - The Optical Society
ISBN (Print)9781943580460
DOIs
StatePublished - 2018
EventFrontiers in Optics, FIO 2018 - Washington, DC, United States
Duration: Sep 16 2018Sep 20 2018

Publication series

NameOptics InfoBase Conference Papers
VolumePart F114-FIO 2018

Other

OtherFrontiers in Optics, FIO 2018
CountryUnited States
CityWashington, DC
Period9/16/189/20/18

All Science Journal Classification (ASJC) codes

  • Electronic, Optical and Magnetic Materials
  • Mechanics of Materials

Fingerprint Dive into the research topics of 'Photonic neural network nonlinear activation functions by electrooptic absorption modulators'. Together they form a unique fingerprint.

  • Cite this

    George, J., Mehrabian, A., Amin, R., El-Ghazawi, T., Prucnal, P. K., & Sorger, V. J. (2018). Photonic neural network nonlinear activation functions by electrooptic absorption modulators. In Frontiers in Optics, FIO 2018 (Optics InfoBase Conference Papers; Vol. Part F114-FIO 2018). OSA - The Optical Society. https://doi.org/10.1364/FIO.2018.JW3A.123