Delay Based Reservoir Computing on Integrated InP Photonic Chip

Krishan Kumar Harkhoe, Guy Verschaffelt, Andrew Katumba, Peter Bienstman, Guy Van Der Sande

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


We have analyzed the performance of a reservoir computing system based on a semiconductor laser with delayed optical output feedback on timeseries prediction and bit parity tests. Both laser and feedback section are fully integrated on an InP based photonic chip fabricated on the Jeppix platform using standard building blocks. We have studied how the system parameters affect the performance and found that this reservoir computing chip reaches processing speeds of 0.9GSa/s with comparable performances as obtained by other non-integrated RC setups based on delayed feedback as well as RC setup on passive silicon photonic chips.
Original languageEnglish
Title of host publicationCognitive Computing
Subtitle of host publicationMerging Concepts with Hardware
Number of pages2
Publication statusPublished - 18 Dec 2018
EventCognitive computing:: merging concepts with hardware - Hannover, Germany
Duration: 18 Dec 201820 Dec 2018


ConferenceCognitive computing:


Dive into the research topics of 'Delay Based Reservoir Computing on Integrated InP Photonic Chip'. Together they form a unique fingerprint.

Cite this