Please use this identifier to cite or link to this item:
Title: Polaritonic neuromorphic computing outperforms linear classifiers
Authors: Ballarini, Dario
Gianfrate, Antonio
Panico, Riccardo
Opala, Andrzej
Ghosh, Sanjib
Dominici, Lorenzo
Ardizzone, Vincenzo
De Giorgi, Milena
Lerario, Giovanni
Gigli, Giuseppe
Liew, Timothy Chi Hin
Matuszewski, Michal
Sanvitto, Daniele
Keywords: Science::Physics::Optics and light
Issue Date: 2020
Source: Ballarini, D., Gianfrate, A., Panico, R., Opala, A., Ghosh, S., Dominici, L., ... Sanvitto, D. (2020). Polaritonic neuromorphic computing outperforms linear classifiers. Nano Letters, 20(5), 3506-3512. doi:10.1021/acs.nanolett.0c00435
Journal: Nano Letters 
Abstract: Machine learning software applications are ubiquitous in many fields of science and society for their outstanding capability to solve computationally vast problems like the recognition of patterns and regularities in big data sets. In spite of these impressive achievements, such processors are still based on the so-called von Neumann architecture, which is a bottleneck for faster and power-efficient neuromorphic computation. Therefore, one of the main goals of research is to conceive physical realizations of artificial neural networks capable of performing fully parallel and ultrafast operations. Here we show that lattices of exciton-polariton condensates accomplish neuromorphic computing with outstanding accuracy thanks to their high optical nonlinearity. We demonstrate that our neural network significantly increases the recognition efficiency compared with the linear classification algorithms on one of the most widely used benchmarks, the MNIST problem, showing a concrete advantage from the integration of optical systems in neural network architectures.
ISSN: 1530-6992
DOI: 10.1021/acs.nanolett.0c00435
Schools: School of Physical and Mathematical Sciences 
Rights: This document is the Accepted Manuscript version of a Published Work that appeared in final form in Nano Letters, copyright © American Chemical Society after peer review and technical editing by the publisher. To access the final edited and published work see
Fulltext Permission: open
Fulltext Availability: With Fulltext
Appears in Collections:SPMS Journal Articles

Files in This Item:
File Description SizeFormat 
Supporting Information.pdfSupporting Information5.07 MBAdobe PDFThumbnail
1911.02923.pdfPreprint Version Main Text5.69 MBAdobe PDFThumbnail

Citations 10

Updated on Nov 26, 2023

Web of ScienceTM
Citations 10

Updated on Oct 25, 2023

Page view(s)

Updated on Nov 30, 2023

Download(s) 20

Updated on Nov 30, 2023

Google ScholarTM




Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.