Efficient Learning for Deep Quantum Neural Networks

2019/02/27 by Kerstin Beer, Dmytro Bondarenko, Terry Farrelly +3 · 5 citations
Physics and Astronomy · Computer Science · #quant-ph #cs.GT #cs.LG #physics.comp-ph

paper · pdf · doi:10.1038/s41467-020-14454-2

published as Nat. Commun. 11, 808 (2020)

arxiv created 2019/02/27 · arxiv updated 2020/04/30

Abstract

Neural networks enjoy widespread success in both research and industry and, with the imminent advent of quantum technology, it is now a crucial challenge to design quantum neural networks for fully quantum learning tasks. Here we propose the use of quantum neurons as a building block for quantum feed-forward neural networks capable of universal quantum computation. We describe the efficient training of these networks using the fidelity as a cost function and provide 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 the optimisation of deep networks. 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.

Cited by

• Non-variational supervised quantum kernel methods: a review
• Scaling Laws for Hybrid Quantum Neural Networks: Depth, Width, and Quantum-Centric Diagnostics
• Indoor Occupancy Classification using a Compact Hybrid Quantum-Classical Model Enabled by a Physics-Informed Radar Digital Twin
• Compton Form Factor Extraction using Quantum Deep Neural Networks
• Trainable Quantum Neural Network for Multiclass Image Classification with the Power of Pre-trained Tree Tensor Networks