Details
| Originalsprache | Englisch |
|---|---|
| Aufsatznummer | 808 |
| Seiten (von - bis) | 808 |
| Fachzeitschrift | Nature Communications |
| Jahrgang | 11 |
| Ausgabenummer | 1 |
| Publikationsstatus | Veröffentlicht - 10 Feb. 2020 |
Abstract
Neural networks enjoy widespread success in both research and industry and, with the advent of quantum technology, it is a crucial challenge to design quantum neural networks for fully quantum learning tasks. Here we propose a truly quantum analogue of classical neurons, which form quantum feedforward neural networks capable of universal quantum computation. We describe the efficient training of these networks using the fidelity as a cost function, providing both classical and efficient quantum implementations. Our method allows for fast optimisation with reduced memory requirements: the number of qudits required scales with only the width, allowing deep-network optimisation. We benchmark our proposal for the quantum task of learning an unknown unitary and find remarkable generalisation behaviour and a striking robustness to noisy training data.
ASJC Scopus Sachgebiete
- Chemie (insg.)
- Allgemeine Chemie
- Biochemie, Genetik und Molekularbiologie (insg.)
- Allgemeine Biochemie, Genetik und Molekularbiologie
- Physik und Astronomie (insg.)
- Allgemeine Physik und Astronomie
Zitieren
- Standard
- Harvard
- Apa
- Vancouver
- BibTex
- RIS
in: Nature Communications, Jahrgang 11, Nr. 1, 808, 10.02.2020, S. 808.
Publikation: Beitrag in Fachzeitschrift › Artikel › Forschung › Peer-Review
}
TY - JOUR
T1 - Training deep quantum neural networks
AU - Beer, Kerstin
AU - Bondarenko, Dmytro
AU - Farrelly, Terry
AU - Osborne, Tobias J.
AU - Salzmann, Robert
AU - Scheiermann, Daniel
AU - Wolf, Ramona
N1 - Funding information: Helpful correspondence and discussions with Lorenzo Cardarelli, Polina Feldmann, Andrew Green, Alexander Hahn, Amit Jamadagni, Maria Kalabakov, Sebastian Kinne-wig, Roger Melko, Laura Niermann, Simone Pfau, Marvin Schwiering, Deniz E. Stiege-mann and E. Miles Stoudenmire are gratefully acknowledged. This work was supported by the DFG through SFB 1227 (DQ-mat), the RTG 1991, and Quantum Frontiers. T.F. was supported by the Australian Research Council Centres of Excellence for Engineered Quantum Systems (EQUS, CE170100009). The publication of this article was funded by the Open Access Fund of the Leibniz Universität Hannover.
PY - 2020/2/10
Y1 - 2020/2/10
N2 - Neural networks enjoy widespread success in both research and industry and, with the advent of quantum technology, it is a crucial challenge to design quantum neural networks for fully quantum learning tasks. Here we propose a truly quantum analogue of classical neurons, which form quantum feedforward neural networks capable of universal quantum computation. We describe the efficient training of these networks using the fidelity as a cost function, providing both classical and efficient quantum implementations. Our method allows for fast optimisation with reduced memory requirements: the number of qudits required scales with only the width, allowing deep-network optimisation. We benchmark our proposal for the quantum task of learning an unknown unitary and find remarkable generalisation behaviour and a striking robustness to noisy training data.
AB - Neural networks enjoy widespread success in both research and industry and, with the advent of quantum technology, it is a crucial challenge to design quantum neural networks for fully quantum learning tasks. Here we propose a truly quantum analogue of classical neurons, which form quantum feedforward neural networks capable of universal quantum computation. We describe the efficient training of these networks using the fidelity as a cost function, providing both classical and efficient quantum implementations. Our method allows for fast optimisation with reduced memory requirements: the number of qudits required scales with only the width, allowing deep-network optimisation. We benchmark our proposal for the quantum task of learning an unknown unitary and find remarkable generalisation behaviour and a striking robustness to noisy training data.
UR - http://www.scopus.com/inward/record.url?scp=85079230673&partnerID=8YFLogxK
U2 - 10.1038/s41467-020-14454-2
DO - 10.1038/s41467-020-14454-2
M3 - Article
C2 - 32041956
AN - SCOPUS:85079230673
VL - 11
SP - 808
JO - Nature Communications
JF - Nature Communications
SN - 2041-1723
IS - 1
M1 - 808
ER -