Standard

Decoding small surface codes with feedforward neural networks. / Varsamopoulos, Savvas; Criger, Ben; Bertels, Koen.

In: Quantum Science and Technology, Vol. 3, No. 1, 015004, 01.01.2018, p. 1-12.

Research output: Contribution to journalArticleScientificpeer-review

Harvard

Varsamopoulos, S, Criger, B & Bertels, K 2018, 'Decoding small surface codes with feedforward neural networks' Quantum Science and Technology, vol. 3, no. 1, 015004, pp. 1-12. https://doi.org/10.1088/2058-9565/aa955a

APA

Varsamopoulos, S., Criger, B., & Bertels, K. (2018). Decoding small surface codes with feedforward neural networks. Quantum Science and Technology, 3(1), 1-12. [015004]. https://doi.org/10.1088/2058-9565/aa955a

Vancouver

Varsamopoulos S, Criger B, Bertels K. Decoding small surface codes with feedforward neural networks. Quantum Science and Technology. 2018 Jan 1;3(1):1-12. 015004. https://doi.org/10.1088/2058-9565/aa955a

Author

Varsamopoulos, Savvas ; Criger, Ben ; Bertels, Koen. / Decoding small surface codes with feedforward neural networks. In: Quantum Science and Technology. 2018 ; Vol. 3, No. 1. pp. 1-12.

BibTeX

@article{2157fc7a569d436d9d0af8ef12ceb18e,
title = "Decoding small surface codes with feedforward neural networks",
abstract = "Surface codes reach high error thresholds when decoded with known algorithms, but the decoding time will likely exceed the available time budget, especially for near-term implementations. To decrease the decoding time, we reduce the decoding problem to a classification problem that a feedforward neural network can solve. We investigate quantum error correction and fault tolerance at small code distances using neural network-based decoders, demonstrating that the neural network can generalize to inputs that were not provided during training and that they can reach similar or better decoding performance compared to previous algorithms. We conclude by discussing the time required by a feedforward neural network decoder in hardware.",
keywords = "artificial neural networks, fault tolerance, quantum error correction, surface codes",
author = "Savvas Varsamopoulos and Ben Criger and Koen Bertels",
year = "2018",
month = "1",
day = "1",
doi = "10.1088/2058-9565/aa955a",
language = "English",
volume = "3",
pages = "1--12",
journal = "Quantum Science and Technology",
issn = "2058-9565",
publisher = "The Institute of Physics Publishing",
number = "1",

}

RIS

TY - JOUR

T1 - Decoding small surface codes with feedforward neural networks

AU - Varsamopoulos, Savvas

AU - Criger, Ben

AU - Bertels, Koen

PY - 2018/1/1

Y1 - 2018/1/1

N2 - Surface codes reach high error thresholds when decoded with known algorithms, but the decoding time will likely exceed the available time budget, especially for near-term implementations. To decrease the decoding time, we reduce the decoding problem to a classification problem that a feedforward neural network can solve. We investigate quantum error correction and fault tolerance at small code distances using neural network-based decoders, demonstrating that the neural network can generalize to inputs that were not provided during training and that they can reach similar or better decoding performance compared to previous algorithms. We conclude by discussing the time required by a feedforward neural network decoder in hardware.

AB - Surface codes reach high error thresholds when decoded with known algorithms, but the decoding time will likely exceed the available time budget, especially for near-term implementations. To decrease the decoding time, we reduce the decoding problem to a classification problem that a feedforward neural network can solve. We investigate quantum error correction and fault tolerance at small code distances using neural network-based decoders, demonstrating that the neural network can generalize to inputs that were not provided during training and that they can reach similar or better decoding performance compared to previous algorithms. We conclude by discussing the time required by a feedforward neural network decoder in hardware.

KW - artificial neural networks

KW - fault tolerance

KW - quantum error correction

KW - surface codes

UR - http://www.scopus.com/inward/record.url?scp=85047974823&partnerID=8YFLogxK

U2 - 10.1088/2058-9565/aa955a

DO - 10.1088/2058-9565/aa955a

M3 - Article

VL - 3

SP - 1

EP - 12

JO - Quantum Science and Technology

T2 - Quantum Science and Technology

JF - Quantum Science and Technology

SN - 2058-9565

IS - 1

M1 - 015004

ER -

ID: 45481611