Training deep quantum neural networks

authored by: Kerstin Beer, Dmytro Bondarenko, Terry Farrelly, Tobias J. Osborne, Robert Salzmann, Daniel Scheiermann, Ramona Wolf
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.
Organisation(s): Institute of Theoretical Physics
QuantumFrontiers
CRC 1227 Designed Quantum States of Matter (DQ-mat)
External Organisation(s): University of Queensland
University of Cambridge
Type: Article
Journal: Nature Communications
Volume: 11
Pages: 808
ISSN: 2041-1723
Publication date: 10.02.2020
Publication status: Published
Peer reviewed: Yes
ASJC Scopus subject areas: Chemistry(all), Biochemistry, Genetics and Molecular Biology(all), Physics and Astronomy(all)
Electronic version(s): https://doi.org/10.1038/s41467-020-14454-2 (Access: Open)
https://doi.org/10.15488/9906 (Access: Open)

BibTeX

@article{49cfaf8b35044a4dbcdb09c2d4d441a5,
title = "Training deep quantum neural networks",
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.",
author = "Kerstin Beer and Dmytro Bondarenko and Terry Farrelly and Osborne, {Tobias J.} and Robert Salzmann and Daniel Scheiermann and Ramona Wolf",
note = "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 Universit{\"a}t Hannover.",
year = "2020",
month = feb,
day = "10",
doi = "10.1038/s41467-020-14454-2",
language = "English",
volume = "11",
pages = "808",
journal = "Nature Communications",
issn = "2041-1723",
publisher = "Nature Publishing Group",
number = "1",
}