Abstract Quantum machine learning (QML) has surged as a prominent area of research with the objective to go beyond the capabilities of classical machine learning models. A critical aspect of any learning task is the process of data embedding, which directly impacts model performance. Poorly designed data-embedding strategies can significantly impact the success of a learning task. Despite its importance, rigorous analyses of data-embedding effects are limited, leaving many cases without effective assessment methods. In this work, we introduce a metric for binary classification tasks, the class margin , by merging the concepts of average randomness and classification margin. This metric analytically connects data-induced randomness with classification accuracy for a given data-embedding map. We benchmark a range of data-embedding strategies through class margin , demonstrating its ability to identify data-induced randomness that hinders classification performance. We expect this work to provide a new approach to evaluate QML models by their data-embedding processes, addressing gaps left by existing analytical toolsAbstract Quantum machine learning (QML) has surged as a prominent area of research with the objective to go beyond the capabilities of classical machine learning models. A critical aspect of any learning task is the process of data embedding, which directly impacts model performance. Poorly designed data-embedding strategies can significantly impact the success of a learning task. Despite its importance, rigorous analyses of data-embedding effects are limited, leaving many cases without effective assessment methods. In this work, we introduce a metric for binary classification tasks, the class margin , by merging the concepts of average randomness and classification margin. This metric analytically connects data-induced randomness with classification accuracy for a given data-embedding map. We benchmark a range of data-embedding strategies through class margin , demonstrating its ability to identify data-induced randomness that hinders classification performance. We expect this work to provide a new approach to evaluate QML models by their data-embedding processes, addressing gaps left by existing analytical tools

arXiv:2411.19281npj Quantum InformationJul 28, 20260 citations

Quantum embedding

Max Nusspickel

May 1, 20210 citations

Representing Data on a Quantum Computer

Maria Schuld, Francesco Petruccione

Quantum science and technologyJan 1, 20218 citations

Identification of quantum generative circuits with parallel quantum neural network

Zheping Wu, Xiaopeng Huang, Hengyue Jia +2 more

The rapid emergence of quantum technology has raised new challenges in distinguishing various quantum circuits of similar functions. In this work, we propose parallel quantum embedding neural network (ParaQuanNet) for the efficient identification of quantum generative circuits via classifications of the corresponding output data. Specifically, we generated W-like states with eight generative quantum circuits realizing the generative quantum denoising diffusion probabilistic models (QDDPM). Our ParaQuanNet can classify these eight classes of generated quantum data with an accuracy of { $99.5\%$ }, even though all of them are trained to generate the same types of quantum data. With a novel design of parallel quantum embedding unit (PQEU) in our neural networks, our ParaQuanNet enables the quantum kernel circuit parallelly process all the receptive fields of quantum data, which empowers the quantum data processing efficiency. We also integrate the mutually unbiased measurements into our ParaQuanNet and further improve its performance. We apply our ParaQuanNet on the classification of classical data sets and demonstrate a good performance of quantum neural networks on these tasks. Our approach demonstrates good robustness to noisy data and the circuit-level noise with a Python realization in a classical GPU. Our results highlight ParaQuanNet as a scalable and effective framework for quantum circuits identification, contributing to the broader development of quantum machine intelligence.The rapid emergence of quantum technology has raised new challenges in distinguishing various quantum circuits of similar functions. In this work, we propose parallel quantum embedding neural network (ParaQuanNet) for the efficient identification of quantum generative circuits via classifications of the corresponding output data. Specifically, we generated W-like states with eight generative quantum circuits realizing the generative quantum denoising diffusion probabilistic models (QDDPM). Our ParaQuanNet can classify these eight classes of generated quantum data with an accuracy of {$99.5\%$}, even though all of them are trained to generate the same types of quantum data. With a novel design of parallel quantum embedding unit (PQEU) in our neural networks, our ParaQuanNet enables the quantum kernel circuit parallelly process all the receptive fields of quantum data, which empowers the quantum data processing efficiency. We also integrate the mutually unbiased measurements into our ParaQuanNet and further improve its performance. We apply our ParaQuanNet on the classification of classical data sets and demonstrate a good performance of quantum neural networks on these tasks. Our approach demonstrates good robustness to noisy data and the circuit-level noise with a Python realization in a classical GPU. Our results highlight ParaQuanNet as a scalable and effective framework for quantum circuits identification, contributing to the broader development of quantum machine intelligence.

quant-pharXiv:2603.02834Frontiers of PhysicsMar 4, 20260 citations

Investigating a Quantum Cloud Paradigm with Quantum Neural Networks

Maxwell Yarter, Glen S. Uehara, Andreas Spanias

In this work, we examine the interactions between an embedded processing board and cloud server performing quantum computing simulations. We examined the trade-offs in performance and complexity between using classical neural networks and quantum-hybrid neural networks on the cloud server. More specifically, we propose the use of quantum hybrid neural network (QNN) for the classification of spoken commands on live audio data acquired at the networks edge. For this application, a compact embedded processor board handles simple operations like data acquisition and pre-processing while a quantum cloud server is used to perform quantum computing simulations. This experimental setup is well suited for quantum computing as it is not feasible to embed a quantum processor at the edge, but practical to interface embedded processor boards to a quantum cloud server for processing massive audio data for a variety of recognition tasks. We found that distributing the task between the embedded processor and quantum sever enabled the application of QNN's to live audio data at the expense of system response time.In this work, we examine the interactions between an embedded processing board and cloud server performing quantum computing simulations. We examined the trade-offs in performance and complexity between using classical neural networks and quantum-hybrid neural networks on the cloud server. More specifically, we propose the use of quantum hybrid neural network (QNN) for the classification of spoken commands on live audio data acquired at the networks edge. For this application, a compact embedded processor board handles simple operations like data acquisition and pre-processing while a quantum cloud server is used to perform quantum computing simulations. This experimental setup is well suited for quantum computing as it is not feasible to embed a quantum processor at the edge, but practical to interface embedded processor boards to a quantum cloud server for processing massive audio data for a variety of recognition tasks. We found that distributing the task between the embedded processor and quantum sever enabled the application of QNN's to live audio data at the expense of system response time.

IEEE International Midwest Symposium on Circuits and Systems (MWSCAS)Aug 6, 20234 citations

Quantum Data Structures and Encoding

Jesse Van Griensven Thé, Roydon Andrew Fraser, José R. Rosas-Bustos

Springer eBooksJan 1, 20250 citations

99.5\%

}, even though all of them are trained to generate the same types of quantum data. With a novel design of parallel quantum embedding unit (PQEU) in our neural networks, our ParaQuanNet enables the quantum kernel circuit parallelly process all the receptive fields of quantum data, which empowers the quantum data processing efficiency. We also integrate the mutually unbiased measurements into our ParaQuanNet and further improve its performance. We apply our ParaQuanNet on the classification of classical data sets and demonstrate a good performance of quantum neural networks on these tasks. Our approach demonstrates good robustness to noisy data and the circuit-level noise with a Python realization in a classical GPU. Our results highlight ParaQuanNet as a scalable and effective framework for quantum circuits identification, contributing to the broader development of quantum machine intelligence.