WDM weighted sum in an 8x8 SOA-based InP cross-connect for photonic deep neural networks

Bin Shi, Nicola Calabretta, D. Bunandar, D. Englund, Ripalta Stabile

Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

6 Citations (Scopus)
1 Downloads (Pure)

Abstract

We demonstrate high fidelity weighted addition of four 10 Gb/s on-off keyed data channels on a SOA-based monolithically integrated cross-connect, with a reading error dispersion below 0.2 with respect to the target. These results open the route to feasible 8x8 one-layer neuron interconnectivity for photonic integrated deep neural networks.

Original languageEnglish
Title of host publicationProceedings of the 2018 Photonics in Switching and Computing, PSC 2018
EditorsKonstantinos Manousakis, Stavros Iezekiel, Ioannis Tomkos, Georgios Ellinas, Katsuyuki Utaka
Place of PublicationPiscataway
PublisherInstitute of Electrical and Electronics Engineers
Number of pages3
ISBN (Electronic)978-1-5386-9392-6
DOIs
Publication statusPublished - 1 Sep 2018
Event2018 International Conference on Photonics in Switching and Computing, PSC 2018 - Limassol, Cyprus
Duration: 19 Sep 201821 Sep 2018

Conference

Conference2018 International Conference on Photonics in Switching and Computing, PSC 2018
CountryCyprus
CityLimassol
Period19/09/1821/09/18

Keywords

  • neuromorphic computing
  • optical cross-connect
  • photonic integrated circuit
  • SOA

Fingerprint Dive into the research topics of 'WDM weighted sum in an 8x8 SOA-based InP cross-connect for photonic deep neural networks'. Together they form a unique fingerprint.

Cite this