| Authors: | K. Harkhoe, G. Verschaffelt, A. Katumba, P. Bienstman, G. Van der Sande | | Title: | Delay Based Reservoir Computing on Integrated InP Photonic Chip | | Format: | International Conference Proceedings | | Publication date: | 12/2018 | | Journal/Conference/Book: | Cognitive Computing: Merging Concepts with Hardware
| | Volume(Issue): | p.2 | | Location: | Hannover, Germany | | Citations: | Look up on Google Scholar
|
Abstract
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. Related Research Topics
Related Projects
|
|
