Continuous-Variable Deep Quantum Neural Networks for Flexible Learning of Structured Classical Information

TL;DR

This paper introduces a continuous-variable quantum neural network model that leverages optical modes to learn structured classical data with high fidelity, demonstrating its potential integration with existing optical communication systems.

Contribution

It presents a novel stacked single mode CV quantum neural network capable of learning structured classical information without size restrictions, using non-linear unitary operations.

Findings

Achieved over 99.98% fidelity on MNIST digit classification

Demonstrated the network's adaptability to structured classical data

Showcased potential integration with optical communication hardware

Abstract

Quantum computation using optical modes has been well-established in its ability to construct deep neural networks. These networks have been shown to be flexible both architecturally as well as in terms of the type of data being processed. We leverage this property of the Continuous-Variable (CV) model to construct stacked single mode networks that are shown to learn structured classical information, while placing no restrictions on the size of the network, and at the same time maintaining it's complexity. The hallmark of the CV model is its ability to forge non-linear functions using a set of gates that allows it to remain completely unitary. The proposed model exemplifies that the appropriate photonic hardware can be integrated with present day optical communication systems to meet our information processing requirements. In this paper, using the Strawberry Fields software library on the MNIST dataset of hand-written digits, we demonstrate the adaptability of the network to learn classical information to fidelities of greater than 99.98%