Transfer Learning in Hybrid Classical-Quantum Neural Networks

By Andrea Mari et al

Published on Oct. 5, 2020

Read the original document by opening this link in a new tab.

Table of Contents

1 Introduction
2 Hybrid classical-quantum networks
3 Transfer learning
3.1 Classical to quantum transfer learning

Summary

Transfer learning is extended to hybrid neural networks composed of classical and quantum elements. The focus is on transfer learning paradigm in quantum machine learning. Various transfer learning schemes are discussed, such as classical to classical (CC), classical to quantum (CQ), quantum to classical (QC), and quantum to quantum (QQ). The potential of transfer learning in quantum machine learning is explored, especially in the context of Noisy Intermediate-Scale Quantum (NISQ) devices. The concept of dressed quantum circuits is introduced for smoother implementation of transfer learning. The paper presents proof-of-principle examples of applying transfer learning in hybrid classical-quantum systems.