Repository logo
 

Training deep quantum neural networks.

Published version
Peer-reviewed

Change log

Authors

Bondarenko, Dmytro 
Osborne, Tobias J 
Salzmann, Robert 

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.

Description

Keywords

51 Physical Sciences, 46 Information and Computing Sciences, 5108 Quantum Physics, 4611 Machine Learning

Journal Title

Nat Commun

Conference Name

Journal ISSN

2041-1723
2041-1723

Volume Title

11

Publisher

Springer Science and Business Media LLC
Sponsorship
Deutsche Forschungsgemeinschaft (German Research Foundation) (SFB 1227, RTG 1991, EXC 2123)