Repository logo
 

Quantum self-supervised learning

Published version
Peer-reviewed

Change log

Authors

Anderson, LW 
Xie, W 
Albanie, S 

Abstract

jats:titleAbstract</jats:title>jats:pThe resurgence of self-supervised learning, whereby a deep learning model generates its own supervisory signal from the data, promises a scalable way to tackle the dramatically increasing size of real-world data sets without human annotation. However, the staggering computational complexity of these methods is such that for state-of-the-art performance, classical hardware requirements represent a significant bottleneck to further progress. Here we take the first steps to understanding whether quantum neural networks (QNNs) could meet the demand for more powerful architectures and test its effectiveness in proof-of-principle hybrid experiments. Interestingly, we observe a numerical advantage for the learning of visual representations using small-scale QNN over equivalently structured classical networks, even when the quantum circuits are sampled with only 100 shots. Furthermore, we apply our best quantum model to classify unseen images on thejats:italicibmq_paris</jats:italic>quantum computer and find that current noisy devices can already achieve equal accuracy to the equivalent classical model on downstream tasks.</jats:p>

Description

Funder: National Research Foundation Singapore; doi: https://doi.org/10.13039/501100001381

Keywords

5108 Quantum Physics, 51 Physical Sciences

Journal Title

Quantum Science and Technology

Conference Name

Journal ISSN

2058-9565
2058-9565

Volume Title

7

Publisher

IOP Publishing
Sponsorship
Engineering and Physical Sciences Research Council (EP/M013243/1, EP/M013774/1, EP/T001062/1)
Visual AI (EP/T028572/1)