An unsupervised feature learning for quantum-classical convolutional network with applications to fault detection

TL;DR

This paper introduces an unsupervised quantum-classical convolutional network that leverages k-means clustering to efficiently learn quantum features, demonstrating effectiveness in fault detection tasks.

Contribution

It presents a novel unsupervised learning approach for quantum-classical CNNs using k-means clustering to enhance quantum feature extraction.

Findings

Effective fault detection in bearing using the proposed method

Unsupervised quantum feature learning reduces quantum resource requirements

Demonstrated improved quantum feature differentiation

Abstract

Combining the advantages of quantum computing and neural networks, quantum neural networks (QNNs) have gained considerable attention recently. However, because of the lack of quantum resource, it is costly to train QNNs. In this work, we presented a simple unsupervised method for quantum-classical convolutional networks to learn a hierarchy of quantum feature extractors. Each level of the resulting feature extractors consist of multiple quanvolution filters, followed by a pooling layer. The main contribution of the proposed approach is to use the $K$-means clustering to maximize the difference of quantum properties in quantum circuit ansatz. One experiment on the bearing fault detection task shows the effectiveness of the proposed method.