Transfer learning in hybrid classical-quantum neural networks

TL;DR

This paper explores transfer learning in hybrid classical-quantum neural networks, focusing on a paradigm where classical networks are augmented with quantum circuits, enabling efficient high-dimensional data processing and quantum feature embedding.

Contribution

It introduces a novel hybrid transfer learning approach with a focus on classical pre-trained networks combined with variational quantum circuits, demonstrated through proof-of-concept experiments.

Findings

Quantum transfer learning enhances image recognition capabilities.

Hybrid models can be effectively implemented on different quantum hardware.

The approach facilitates embedding informative features into quantum processors.

Abstract

We extend the concept of transfer learning, widely applied in modern machine learning algorithms, to the emerging context of hybrid neural networks composed of classical and quantum elements. We propose different implementations of hybrid transfer learning, but we focus mainly on the paradigm in which a pre-trained classical network is modified and augmented by a final variational quantum circuit. This approach is particularly attractive in the current era of intermediate-scale quantum technology since it allows to optimally pre-process high dimensional data (e.g., images) with any state-of-the-art classical network and to embed a select set of highly informative features into a quantum processor. We present several proof-of-concept examples of the convenient application of quantum transfer learning for image recognition and quantum state classification. We use the cross-platform software library PennyLane to experimentally test a high-resolution image classifier with two different quantum computers, respectively provided by IBM and Rigetti.