arXiv:2310.12559

Application of quantum neural network model to a multivariate regression problem

Hirotoshi Hirai

Published Oct 19, 2023• 4 citations

Abstract

Since the introduction of the quantum neural network model, it has been widely studied due to its strong expressive power and robustness to overfitting. To date, the model has been evaluated primarily in classification tasks, but its performance in practical multivariate regression problems has not been thoroughly examined. In this study, the Auto-MPG data set (392 valid data points, excluding missing data, on fuel efficiency for various vehicles) was used to construct QNN models and investigate the effect of the size of the training data on generalization performance. The results indicate that QNN is particularly effective when the size of training data is small, suggesting that it is especially suitable for small-data problems such as those encountered in Materials Informatics.

DOI: 10.48550/arxiv.2310.12559

Related papers

Practical application of quantum neural network to materials informatics

Hirotoshi Hirai

Quantum neural network (QNN) models have received increasing attention owing to their strong expressibility and resistance to overfitting. It is particularly useful when the size of the training data is small, making it a good fit for materials informatics (MI) problems. However, there are only a few examples of the application of QNN to multivariate regression models, and little is known about how these models are constructed. This study aims to construct a QNN model to predict the melting points of metal oxides as an example of a multivariate regression task for the MI problem. Different architectures (encoding methods and entangler arrangements) are explored to create an effective QNN model. Shallow-depth ansatzs could achieve sufficient expressibility using sufficiently entangled circuits. The "linear" entangler was adequate for providing the necessary entanglement. The expressibility of the QNN model could be further improved by increasing the circuit width. The generalization performance could also be improved, outperforming the classical NN model. No overfitting was observed in the QNN models with a well-designed encoder. These findings suggest that QNN can be a useful tool for MI.

Scientific ReportsApr 13, 202414 citations

Practical application of quantum neural network to materials informatics: prediction of the melting points of metal oxides

Hirotoshi Hirai

arXiv:2310.17935Oct 27, 20231 citation

ℤ2 × ℤ2 Equivariant Quantum Neural Networks: Benchmarking against Classical Neural Networks

Zhongtian Dong, Marçal Comajoan Cara, Gopal Ramesh Dahale +8 more

This paper presents a comparative analysis of the performance of Equivariant Quantum Neural Networks (EQNNs) and Quantum Neural Networks (QNNs), juxtaposed against their classical counterparts: Equivariant Neural Networks (ENNs) and Deep Neural Networks (DNNs). We evaluate the performance of each network with three two-dimensional toy examples for a binary classification task, focusing on model complexity (measured by the number of parameters) and the size of the training dataset. Our results show that the Z2×Z2 EQNN and the QNN provide superior performance for smaller parameter sets and modest training data samples.

arXiv:2311.18744AxiomsMar 13, 20245 citations

Regression and Classification with Single-Qubit Quantum Neural Networks

Leandro Carlos de Souza, Bruno Clemente Guingo, Gilson Antonio Giraldi +1 more

The literature reflects a mutually beneficial relationship between machine learning and quantum computing, where progress in one field frequently drives improvements in the other. Motivated by the rich connection between these areas, we use a resource-efficient and scalable Single-Qubit Quantum Neural Network (SQQNN) for both regression and classification tasks using a new data uploading technique. The SQQNN leverages parameterized single-qubit unitary operators and quantum measurements to achieve efficient learning. To train the model, we use gradient descent for regression tasks. For classification, we introduce a novel training method inspired by polynomial regression, which can efficiently find a global minimizer of the transformed least-squares objective in a single step. This approach significantly accelerates training compared to iterative methods. Evaluated across various applications, the SQQNN exhibits virtually error-free and strong performance in regression and classification tasks, including Wisconsin Breast Cancer and MNIST datasets. These results demonstrate the versatility, scalability, and suitability of the SQQNN for deployment on near-term quantum devices.

arXiv:2412.09486Dec 12, 20241 citation

Hybrid Quantum Neural Network Model with Catalyst Experimental Validation: Application for the Dry Reforming of Methane

Jiwon Roh, Seunghyeon Oh, Donggyun Lee +5 more

Machine learning (ML), which has been increasingly applied to complex problems such as catalyst development, encounters challenges in data collection and structuring. Quantum neural networks (QNNs) outperform classical ML models, such as artificial neural networks (ANNs), in prediction accuracy, even with limited data. However, QNNs have limited available qubits. To address this issue, we introduce a hybrid QNN model, combining a parametrized quantum circuit with an ANN structure. We used the catalyst data sets of the dry reforming of methane reaction from the literature and in-house experimental results to compare the hybrid QNN and the ANN models. The hybrid QNN exhibited superior prediction accuracy and a faster convergence rate, achieving an R 2 of 0.942 at 2478 epochs, whereas the ANN achieved an R 2 of 0.935 at 3175 epochs. For the 224 in-house experimental data points previously unreported in the literature, the hybrid QNN exhibited an enhanced generalization performance. It showed a mean absolute error (MAE) of 13.42, compared with an MAE of 27.40 for the ANN under similar training conditions. This study highlights the potential of the hybrid QNN as a powerful tool for solving complex problems in catalysis and chemistry, demonstrating its advantages over classical ML models.

ACS Sustainable Chemistry & EngineeringFeb 23, 202414 citations

Expressibility-Enhancing Strategies for Quantum Neural Networks

Yalin Liao, Junpeng Zhan

Quantum neural networks (QNNs), represented by parameterized quantum circuits, can be trained in the paradigm of supervised learning to map input data to predictions. Much work has focused on theoretically analyzing the expressive power of QNNs. However, in almost all literature, QNNs' expressive power is numerically validated using only simple univariate functions. We surprisingly discover that state-of-the-art QNNs with strong expressive power can have poor performance in approximating even just a simple sinusoidal function. To fill the gap, we propose four expressibility-enhancing strategies for QNNs: Sinusoidal-friendly embedding, redundant measurement, post-measurement function, and random training data. We analyze the effectiveness of these strategies via mathematical analysis and/or numerical studies including learning complex sinusoidal-based functions. Our results from comparative experiments validate that the four strategies can significantly increase the QNNs' performance in approximating complex multivariable functions and reduce the quantum circuit depth and qubits required.

arXiv:2211.12670Nov 23, 20223 citations