All-Photonic Artificial Neural Network Processor Via Nonlinear Optics

Jasvith Raj Basani; Stefan Krastanov; Mikkel Heuck; Dirk R. Englund

doi:10.1364/CLEO_SI.2022.SF4F.5

All-Photonic Artificial Neural Network Processor Via Nonlinear Optics

Jasvith Raj Basani
, Stefan Krastanov
, Mikkel Heuck
, Dirk R. Englund

University of Maryland, College Park
Massachusetts Institute of Technology

Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review

Abstract

We propose an all-photonic architecture to accelerate linear matrix processing by encoding information in the amplitudes of frequency states. Our design is unique in providing a unitary, reversible mode of computation at high speeds.

Original language	English
Title of host publication	Proceedings of Conference on Lasers and Electro-Optics
Number of pages	2
Publisher	Optica Publishing Group
Publication date	2022
Article number	SF4F.5
ISBN (Electronic)	978-1-957171-05-0
DOIs	https://doi.org/10.1364/CLEO_SI.2022.SF4F.5
Publication status	Published - 2022
Event	CLEO: Science and Innovations 2022 - San Jose, United States Duration: 15 May 2022 → 20 May 2022

Conference

Conference	CLEO: Science and Innovations 2022
Country/Territory	United States
City	San Jose
Period	15/05/2022 → 20/05/2022

Access to Document

10.1364/CLEO_SI.2022.SF4F.5

OpenUrl availability

Check availability in DTU Findit

Cite this

@inproceedings{b13ee9bce03b4a208fecc496213132d3,

title = "All-Photonic Artificial Neural Network Processor Via Nonlinear Optics",

abstract = "We propose an all-photonic architecture to accelerate linear matrix processing by encoding information in the amplitudes of frequency states. Our design is unique in providing a unitary, reversible mode of computation at high speeds.",

author = "Basani, \{Jasvith Raj\} and Stefan Krastanov and Mikkel Heuck and Englund, \{Dirk R.\}",

year = "2022",

doi = "10.1364/CLEO\_SI.2022.SF4F.5",

language = "English",

booktitle = "Proceedings of Conference on Lasers and Electro-Optics",

publisher = "Optica Publishing Group",

note = "CLEO: Science and Innovations 2022 ; Conference date: 15-05-2022 Through 20-05-2022",

}

TY - GEN

T1 - All-Photonic Artificial Neural Network Processor Via Nonlinear Optics

AU - Basani, Jasvith Raj

AU - Krastanov, Stefan

AU - Heuck, Mikkel

AU - Englund, Dirk R.

PY - 2022

Y1 - 2022

N2 - We propose an all-photonic architecture to accelerate linear matrix processing by encoding information in the amplitudes of frequency states. Our design is unique in providing a unitary, reversible mode of computation at high speeds.

AB - We propose an all-photonic architecture to accelerate linear matrix processing by encoding information in the amplitudes of frequency states. Our design is unique in providing a unitary, reversible mode of computation at high speeds.

U2 - 10.1364/CLEO_SI.2022.SF4F.5

DO - 10.1364/CLEO_SI.2022.SF4F.5

M3 - Article in proceedings

BT - Proceedings of Conference on Lasers and Electro-Optics

PB - Optica Publishing Group

T2 - CLEO: Science and Innovations 2022

Y2 - 15 May 2022 through 20 May 2022

ER -

All-Photonic Artificial Neural Network Processor Via Nonlinear Optics

Abstract

Conference

Access to Document

OpenUrl availability

Fingerprint

Cite this