Tối ưu hóa nhân lượng tử huấn luyện được và so sánh với học máy trong bài toán phân loại hai giống gạo có ngoại hình gần tương đồng với lượng dữ liệu hạn chế
Abstract
This study evaluates quantum kernels for classifying morphologically overlapping Cammeo and Osmancik rice grains under limited training data. Six outer splits were retained for the broad descriptive benchmark; confirmatory analyses used 10 outer splits, two training seeds, and N = 20, 40, 60, 80, 120, and 200. In the matched ablation, the trainable quantum kernel Q1 exceeded its fixed counterpart by 5.35 percentage points at N = 20 (Holm-adjusted p = 0.0117). The adaptive quantum kernel Q2 exceeded the matched RBF-SVM by 0.19 – 2.18 percentage points and was significant after Holm correction at N = 80 and 200, although the differences at these sizes remained small within the practical equivalence margin of ±2 percentage points. No training size showed a significant difference from the matched linear SVM; TOST supported practical equivalence for N = 40 – 200. Removing the anti-concentration term did not change balanced accuracy; the term was inactive in the inspected training logs. The parameterized quantum kernels were competitive under the evaluated protocol, but the results do not establish a general quantum advantage.
Tóm tắt
Nghiên cứu đánh giá nhân lượng tử trong phân loại gạo Cammeo và Osmancik có hình thái tương đồng với dữ liệu huấn luyện hạn chế. Sáu phép chia ngoài để mô tả; phân tích xác nhận dùng 10 phép chia ngoài, hai khởi tạo huấn luyện và N = 20, 40, 60, 80, 120, 200. Trong đối chứng ghép cặp, nhân Q1 huấn luyện được cao hơn Q1 cố định 5,35 điểm phần trăm tại N = 20 (p Holm = 0,0117). Q2 thích nghi cao hơn RBF-SVM ghép cặp 0,19 – 2,18 điểm phần trăm, có ý nghĩa sau Holm tại N = 80 và 200, nhưng chênh lệch vẫn trong biên tương đương ±2 điểm phần trăm. So với SVM tuyến tính ghép cặp, không cỡ mẫu nào có khác biệt có ý nghĩa; TOST hỗ trợ tương đương thực tế tại N = 40 – 200. Bỏ số hạng chống tập trung không đổi BA; số hạng này không được kích hoạt trong nhật ký đã kiểm tra. Kết quả cho thấy nhân lượng tử có tham số cạnh tranh trong cấu hình khảo sát, nhưng chưa chứng minh ưu thế lượng tử tổng quát.
Article Details

This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
Tài liệu tham khảo
Abbas, A., Sutter, D., Zoufal, C., Lucchi, A., Figalli, A., & Woerner, S. (2021). The power of quantum neural networks. Nature Computational Science, 1(6), 403–409. https://doi.org/10.1038/s43588-021-00084-1
Bergholm, V., Izaac, J., Schuld, M., Gogolin, C., Ahmed, S., Ajith, V., Alam, M. S., Alonso-Linaje, G.,... & Killoran, N. (2018). PennyLane: Automatic differentiation of hybrid quantum-classical computations [Preprint]. arXiv. https://doi.org/10.48550/arXiv.1811.04968
Biamonte, J., Wittek, P., Pancotti, N., Rebentrost, P., Wiebe, N., & Lloyd, S. (2017). Quantum machine learning. Nature, 549(7671), 195–202. https://doi.org/10.1038/nature23474
Boser, B. E., Guyon, I. M., & Vapnik, V. N. (1992). A training algorithm for optimal margin classifiers. In D. Haussler (Ed.), Proceedings of the fifth annual workshop on Computational learning theory (pp. 144–152). ACM. https://doi.org/10.1145/130385.130401
Bowles, J., Ahmed, S., & Schuld, M. (2024). Better than classical? The subtle art of benchmarking quantum machine learning models [Preprint]. arXiv. https://doi.org/10.48550/arXiv.2403.07059
Breiman, L. (2001). Random forests. Machine Learning, 45(1), 5–32. https://doi.org/10.1023/A:1010933404324
Brodersen, K. H., Ong, C. S., Stephan, K. E., & Buhmann, J. M. (2010). The balanced accuracy and its posterior distribution. In 2010 20th International Conference on Pattern Recognition (pp. 3121–3124). IEEE. https://doi.org/10.1109/ICPR.2010.764
Butler, K. T., Davies, D. W., Cartwright, H., Isayev, O., & Walsh, A. (2018). Machine learning for molecular and materials science. Nature, 559(7715), 547–555. https://doi.org/10.1038/s41586-018-0337-2
Cawley, G. C., & Talbot, N. L. C. (2010). On over-fitting in model selection and subsequent selection bias in performance evaluation. Journal of Machine Learning Research, 11, 2079–2107. https://www.jmlr.org/papers/v11/cawley10a.html
Çelik, A. (2024). Evaluating the impact of data normalization on rice classification using machine learning algorithms. Acadlore Transactions on AI and Machine Learning, 3(3), 162–171. https://doi.org/10.56578/ataiml030303
Cerezo, M., Arrasmith, A., Babbush, R., Benjamin, S. C., Endo, S., Fujii, K., McClean, J. R., Mitarai, K., Yuan, X., Cincio, L., & Coles, P. J. (2021). Variational quantum algorithms. Nature Reviews Physics, 3(9), 625–644. https://doi.org/10.1038/s42254-021-00348-9
Chatnuntawech, I., Tantisantisom, K., Khanchaitit, P., Boonkoom, T., Bilgic, B., & Chuangsuwanich, E. (2018). Rice classification using spatio-spectral deep convolutional neural network [Preprint]. arXiv. https://doi.org/10.48550/arXiv.1805.11491
Cinar, I., & Koklu, M. (2019). Classification of rice varieties using artificial intelligence methods. International Journal of Intelligent Systems and Applications in Engineering, 7(3), 188–194. https://doi.org/10.18201/ijisae.2019355381
Cortes, C., & Vapnik, V. (1995). Support-vector networks. Machine Learning, 20(3), 273–297. https://doi.org/10.1007/BF00994018
Cox, D. R. (1958). The regression analysis of binary sequences. Journal of the Royal Statistical Society: Series B (Methodological), 20(2), 215–242. https://doi.org/10.1111/j.2517-6161.1958.tb00292.x
Cristianini, N., Shawe-Taylor, J., Elisseeff, A., & Kandola, J. S. (2002). On kernel-target alignment. In T. G. Dietterich, S. Becker, & Z. Ghahramani (Eds.), Advances in Neural Information Processing Systems 14 (pp. 367–374). MIT Press. https://doi.org/10.7551/mitpress/1120.003.0052
Efron, B. (1979). Bootstrap methods: Another look at the jackknife. The Annals of Statistics, 7(1), 1–26. https://doi.org/10.1214/aos/1176344552
Fawcett, T. (2006). An introduction to ROC analysis. Pattern Recognition Letters, 27(8), 861–874. https://doi.org/10.1016/j.patrec.2005.10.010
Friedman, J. H. (2001). Greedy function approximation: A gradient boosting machine. The Annals of Statistics, 29(5), 1189–1232. https://doi.org/10.1214/aos/1013203451
Gentinetta, G., Sutter, D., Zoufal, C., Fuller, B., & Woerner, S. (2023). Quantum kernel alignment with stochastic gradient descent. In 2023 IEEE International Conference on Quantum Computing and Engineering (QCE) (Vol. 1, pp. 256–262). IEEE. https://doi.org/10.1109/QCE57702.2023.00036
Geurts, P., Ernst, D., & Wehenkel, L. (2006). Extremely randomized trees. Machine Learning, 63(1), 3–42.
https://doi.org/10.1007/s10994-006-6226-1
Havlíček, V., Córcoles, A. D., Temme, K., Harrow, A. W., Kandala, A., Chow, J. M., & Gambetta, J. M. (2019). Supervised learning with quantum-enhanced feature spaces. Nature, 567(7747), 209–212.
https://doi.org/10.1038/s41586-019-0980-2
Holm, S. (1979). A simple sequentially rejective multiple test procedure. Scandinavian Journal of Statistics, 6(2), 65–70. https://www.jstor.org/stable/4615733
Huang, H.-Y., Broughton, M., Mohseni, M., Babbush, R., Boixo, S., Neven, H., & McClean, J. R. (2021). Power of data in quantum machine learning. Nature Communications, 12(1), 2631. https://doi.org/10.1038/s41467-021-22539-9
Hubregtsen, T., Wierichs, D., Gil-Fuster, E., Derks, P.-J. H. S., Faehrmann, P. K., & Meyer, J. J. (2022). Training quantum embedding kernels on near-term quantum computers. Physical Review A, 106(4), 042431. https://doi.org/10.1103/PhysRevA.106.042431
Kakavand, S., Strohmeyer, C., & Schlotter, M. (2026). Benchmarking quantum kernel support vector machines against classical baselines on tabular data: A rigorous empirical study with hardware validation [Preprint]. arXiv. https://doi.org/10.48550/arXiv.2604.18837
Kingma, D. P., & Ba, J. (2015). Adam: A method for stochastic optimization. In 3rd International Conference on Learning Representations (ICLR). https://arxiv.org/abs/1412.6980
Lakens, D. (2017). Equivalence tests: A practical primer for t tests, correlations, and meta-analyses. Social Psychological and Personality Science, 8(4), 355–362. https://doi.org/10.1177/1948550617697177
Le, H. N., Pham, T. B. T., Truong, D. A. K., Vo, K. D., & Nguyen, T. T. (2026). Efficient molecular dynamics simulation of 2D penta-silicene materials using machine learning potentials [Preprint]. arXiv. https://doi.org/10.48550/arXiv.2602.11548
Liu, Y., Arunachalam, S., & Temme, K. (2021). A rigorous and robust quantum speed-up in supervised machine learning. Nature Physics, 17(9), 1013–1017. https://doi.org/10.1038/s41567-021-01287-z
Loshchilov, I., & Hutter, F. (2019). Decoupled weight decay regularization. In 7th International Conference on Learning Representations (ICLR). https://openreview.net/forum?id=Bkg6RiCqY7
McClean, J. R., Boixo, S., Smelyanskiy, V. N., Babbush, R., & Neven, H. (2018). Barren plateaus in quantum neural network training landscapes. Nature Communications, 9(1), 4812. https://doi.org/10.1038/s41467-018-07090-4
Merchant, A., Batzner, S., Schoenholz, S. S., Aykol, M., Cheon, G., & Cubuk, E. D. (2023). Scaling deep learning for materials discovery. Nature, 624(7990), 80–85. https://doi.org/10.1038/s41586-023-06735-9
Mitarai, K., Negoro, M., Kitagawa, M., & Fujii, K. (2018). Quantum circuit learning. Physical Review A, 98(3), 032309. https://doi.org/10.1103/PhysRevA.98.032309
Park, D. K., Blank, C., & Petruccione, F. (2020). The theory of the quantum kernel-based binary classifier. Physics Letters A, 384(21), 126422. https://doi.org/10.1016/j.physleta.2020.126422
Paszke, A., Gross, S., Massa, F., Lerer, A., Bradbury, J., Chanan, G., Killeen, T., Lin, Z., Gimelshein, N., Antiga, L., Desmaison, A., Köpf, A., Yang, E., DeVito, Z., Raison, M., Tejani, A., Chilamkurthy, S., Steiner, B., Fang, L., … Chintala, S. (2019). PyTorch: An imperative style, high-performance deep learning library. In H. Wallach, H. Larochelle, A. Beygelzimer, F. d’Alché-Buc, E. Fox, & R. Garnett (Eds.), Advances in Neural Information Processing Systems (Vol. 32, pp. 8024–8035). Curran Associates. https://papers.nips.cc/paper_files/paper/2019/hash/bdbca288fee7f92f2bfa9f7012727740-Abstract.html
Pearson, K. (1901). On lines and planes of closest fit to systems of points in space. The London, Edinburgh, and Dublin Philosophical Magazine and Journal of Science, 2(11), 559–572. https://doi.org/10.1080/14786440109462720
Pedregosa, F., Varoquaux, G., Gramfort, A., Michel, V., Thirion, B., Grisel, O., Blondel, M., Prettenhofer, P., Weiss, R., Dubourg, V., Vanderplas, J., Passos, A., Cournapeau, D., Brucher, M., Perrot, M., & Duchesnay, É. (2011). Scikit-learn: Machine learning in Python. Journal of Machine Learning Research, 12(85), 2825–2830. https://www.jmlr.org/papers/v12/pedregosa11a.html
Pérez-Salinas, A., Cervera-Lierta, A., Gil-Fuster, E., & Latorre, J. I. (2020). Data re-uploading for a universal quantum classifier. Quantum, 4, 226. https://doi.org/10.22331/q-2020-02-06-226
Phan, T.-T.-H., Vo, Q.-T., & Nguyen, H.-D. (2024). A novel method for identifying rice seed purity using hybrid machine learning algorithms. Heliyon, 10(14), e33941. https://doi.org/10.1016/j.heliyon.2024.e33941
Rumelhart, D. E., Hinton, G. E., & Williams, R. J. (1986). Learning representations by back-propagating errors. Nature, 323(6088), 533–536. https://doi.org/10.1038/323533a0
Schmidt, J., Marques, M. R. G., Botti, S., & Marques, M. A. L. (2019). Recent advances and applications of machine learning in solid-state materials science. Npj Computational Materials, 5(1), 83.
https://doi.org/10.1038/s41524-019-0221-0
Schnabel, J., & Roth, M. (2025). Quantum kernel methods under scrutiny: A benchmarking study. Quantum Machine Intelligence, 7(1), 58. https://doi.org/10.1007/s42484-025-00273-5
Schuirmann, D. J. (1987). A comparison of the two one-sided tests procedure and the power approach for assessing the equivalence of average bioavailability. Journal of Pharmacokinetics and Biopharmaceutics, 15(6), 657–680. https://doi.org/10.1007/BF01068419
Schuld, M. (2021). Supervised quantum machine learning models are kernel methods [Preprint]. arXiv. https://doi.org/10.48550/arXiv.2101.11020
Schuld, M., & Killoran, N. (2019). Quantum machine learning in feature hilbert spaces. Physical Review Letters, 122(4), 040504. https://doi.org/10.1103/PhysRevLett.122.040504
Schuld, M., Sinayskiy, I., & Petruccione, F. (2015). An introduction to quantum machine learning. Contemporary Physics, 56(2), 172–185. https://doi.org/10.1080/00107514.2014.964942
Schuld, M., Sweke, R., & Meyer, J. J. (2021). Effect of data encoding on the expressive power of variational quantum-machine-learning models. Physical Review A, 103(3), 032430. https://doi.org/10.1103/PhysRevA.103.032430
Sim, S., Johnson, P. D., & Aspuru-Guzik, A. (2019). Expressibility and entangling capability of parameterized quantum circuits for hybrid quantum-classical algorithms. Advanced Quantum Technologies, 2(12), 1900070. https://doi.org/10.1002/qute.201900070
Slattery, L., Shaydulin, R., Chakrabarti, S., Pistoia, M., Khairy, S., & Wild, S. M. (2023). Numerical evidence against advantage with quantum fidelity kernels on classical data. Physical Review A, 107(6), 062417. https://doi.org/10.1103/PhysRevA.107.062417
Sweke, R., Wilde, F., Meyer, J. J., Schuld, M., Fährmann, P. K., Meynard-Piganeau, B., & Eisert, J. (2020). Stochastic gradient descent for hybrid quantum-classical optimization. Quantum, 4, 314.
https://doi.org/10.22331/q-2020-08-31-314
Thanasilp, S., Wang, S., Cerezo, M., & Holmes, Z. (2024). Exponential concentration in quantum kernel methods. Nature Communications, 15(1), 5200.
https://doi.org/10.1038/s41467-024-49287-w
UCI Machine Learning Repository. (2019). Rice (cammeo and osmancik). University of California, Irvine. https://doi.org/10.24432/C5MW4Z
Varma, S., & Simon, R. (2006). Bias in error estimation when using cross-validation for model selection. BMC Bioinformatics, 7(1), 91. https://doi.org/10.1186/1471-2105-7-91
Wilcoxon, F. (1945). Individual comparisons by ranking methods. Biometrics Bulletin, 1(6), 80–83.
https://doi.org/10.2307/3001968