Image classification with a 3-Layer SOA-based photonic integrated neural network

B. Shi; N. Calabretta; R. Stabile

doi:10.23919/PS.2019.8817694

Image classification with a 3-Layer SOA-based photonic integrated neural network

Electro-Optical Communication

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

7 Citations (Scopus)

3 Downloads (Pure)

Abstract

We demonstrate for the first time Iris flowers classification by implementing a trained 3-layer neural network with an SOA-based InP cross-connect chip. Classification accuracy of 85.8% is achieved, 9.2% lower than what obtained via a computer.

Original language	English
Title of host publication	OECC/PSC 2019 - 24th OptoElectronics and Communications Conference/International Conference Photonics in Switching and Computing 2019
Place of Publication	Piscataway
Publisher	Institute of Electrical and Electronics Engineers
Number of pages	3
ISBN (Electronic)	978-4-88552-321-2
DOIs	https://doi.org/10.23919/PS.2019.8817694
Publication status	Published - 1 Jul 2019
Event	24th Optoelectronics and Communications Conference, OECC 2019/ International Conference on Photonics in Switching and Computing, PSC 2019 - Fukuoka, Japan Duration: 7 Jul 2019 → 11 Jul 2019 Conference number: 24 https://www.oeccpsc2019.org/

Conference

Conference	24th Optoelectronics and Communications Conference, OECC 2019/ International Conference on Photonics in Switching and Computing, PSC 2019
Abbreviated title	OECC/PSC 2019
Country/Territory	Japan
City	Fukuoka
Period	7/07/19 → 11/07/19
Internet address	https://www.oeccpsc2019.org/

Funding

This research work is financially supported by the Netherlands Organization of Scientific Research (NWO) under the Zwaartekracht programma, ‘Research Centre for Integrated Nanophotonics’.

Keywords

Neuromorphic computing
Photonic integrated circuits

Access to Document

10.23919/PS.2019.8817694

Cite this

Shi, B., Calabretta, N., & Stabile, R. (2019). Image classification with a 3-Layer SOA-based photonic integrated neural network. In OECC/PSC 2019 - 24th OptoElectronics and Communications Conference/International Conference Photonics in Switching and Computing 2019 Article 8817694 Institute of Electrical and Electronics Engineers. https://doi.org/10.23919/PS.2019.8817694

@inproceedings{90c13168a5ce43c089742dabc72aeb53,

title = "Image classification with a 3-Layer SOA-based photonic integrated neural network",

abstract = "We demonstrate for the first time Iris flowers classification by implementing a trained 3-layer neural network with an SOA-based InP cross-connect chip. Classification accuracy of 85.8\% is achieved, 9.2\% lower than what obtained via a computer.",

keywords = "Neuromorphic computing, Photonic integrated circuits",

author = "B. Shi and N. Calabretta and R. Stabile",

year = "2019",

month = jul,

day = "1",

doi = "10.23919/PS.2019.8817694",

language = "English",

booktitle = "OECC/PSC 2019 - 24th OptoElectronics and Communications Conference/International Conference Photonics in Switching and Computing 2019",

publisher = "Institute of Electrical and Electronics Engineers",

address = "United States",

note = "24th Optoelectronics and Communications Conference, OECC 2019/ International Conference on Photonics in Switching and Computing, PSC 2019, OECC/PSC 2019 ; Conference date: 07-07-2019 Through 11-07-2019",

url = "https://www.oeccpsc2019.org/",

}

Shi, B , Calabretta, N & Stabile, R 2019, Image classification with a 3-Layer SOA-based photonic integrated neural network. in OECC/PSC 2019 - 24th OptoElectronics and Communications Conference/International Conference Photonics in Switching and Computing 2019., 8817694, Institute of Electrical and Electronics Engineers, Piscataway, 24th Optoelectronics and Communications Conference, OECC 2019/ International Conference on Photonics in Switching and Computing, PSC 2019, Fukuoka, Japan, 7/07/19. https://doi.org/10.23919/PS.2019.8817694

Image classification with a 3-Layer SOA-based photonic integrated neural network. / Shi, B.; Calabretta, N.; Stabile, R.
OECC/PSC 2019 - 24th OptoElectronics and Communications Conference/International Conference Photonics in Switching and Computing 2019. Piscataway: Institute of Electrical and Electronics Engineers, 2019. 8817694.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

TY - GEN

T1 - Image classification with a 3-Layer SOA-based photonic integrated neural network

AU - Shi, B.

AU - Calabretta, N.

AU - Stabile, R.

N1 - Conference code: 24

PY - 2019/7/1

Y1 - 2019/7/1

N2 - We demonstrate for the first time Iris flowers classification by implementing a trained 3-layer neural network with an SOA-based InP cross-connect chip. Classification accuracy of 85.8% is achieved, 9.2% lower than what obtained via a computer.

AB - We demonstrate for the first time Iris flowers classification by implementing a trained 3-layer neural network with an SOA-based InP cross-connect chip. Classification accuracy of 85.8% is achieved, 9.2% lower than what obtained via a computer.

KW - Neuromorphic computing

KW - Photonic integrated circuits

UR - https://www.scopus.com/pages/publications/85072333575

U2 - 10.23919/PS.2019.8817694

DO - 10.23919/PS.2019.8817694

M3 - Conference contribution

BT - OECC/PSC 2019 - 24th OptoElectronics and Communications Conference/International Conference Photonics in Switching and Computing 2019

PB - Institute of Electrical and Electronics Engineers

CY - Piscataway

T2 - 24th Optoelectronics and Communications Conference, OECC 2019/ International Conference on Photonics in Switching and Computing, PSC 2019

Y2 - 7 July 2019 through 11 July 2019

ER -

Image classification with a 3-Layer SOA-based photonic integrated neural network

Abstract

Conference

Funding

Keywords

Access to Document

Other files and links

Fingerprint

Cite this