Quantum Iris Classifier: A Pennylane-Based Approach
Keywords:
quantum machine learning, pennylane, quantum neural network, iris dataset, hybrid quantum-classical modeAbstract
The advancement of quantum computing has opened new opportunities in data processing and machine learning, particularly through the implementation of efficient variational quantum algorithms. This study explores the implementation of a Quantum Neural Network (QNN) using the Pennylane framework to perform multi-class classification on the classical Iris dataset. By designing a quantum ansatz composed of rotation parameters and CNOT entanglement gates, the model is trained using the Gradient Descent algorithm to minimize a loss function based on softmax cross-entropy. The training process is conducted over 200 epochs, with accuracy and loss evaluations recorded every 10 iterations. Experimental results show that this approach can achieve a maximum accuracy of 96.67% in certain iterations and maintain stable performance above 93% throughout most epochs. This study highlights the potential of hybrid classical-quantum models as a competitive alternative to traditional learning methods, paving the way for broader applications of quantum technologies in small- to medium-scale data classificationReferences
M. Avramouli, I. K. Savvas, A. Vasilaki, and G. Garani, “Unlocking the Potential of Quantum Machine Learning to Advance Drug Discovery,” 2023. doi: 10.3390/electronics12112402.
C. H. Papadimitriou, “Computational complexity,” in Encyclopedia of Computer Science, GBR: John Wiley and Sons Ltd., 2003, pp. 260–265.
N. Schetakis, D. Aghamalyan, P. Griffin, and M. Boguslavsky, “Review of some existing QML frameworks and novel hybrid classical–quantum neural networks realising binary classification for the noisy datasets,” Sci. Rep., vol. 12, no. 1, p. 11927, 2022, doi: 10.1038/s41598-022-14876-6.
M. Zhang, X. Chen, and Z. Liu, “Quantum Neural Network Image Three-Classification Model Based on the Iris Dataset,” in 2024 5th International Conference on Computer Engineering and Application (ICCEA), 2024, pp. 841–846. doi: 10.1109/ICCEA62105.2024.10603623.
F. Rodríguez-Díaz, J. F. Torres, D. Gutiérrez-Avilés, A. Troncoso, and F. Martínez-Álvarez, “An Experimental Comparison of Qiskit and Pennylane for Hybrid Quantum-Classical Support Vector Machines BT - Advances in Artificial Intelligence,” A. Alonso-Betanzos, B. Guijarro-Berdiñas, V. Bolón-Canedo, E. Hernández-Pereira, O. Fontenla-Romero, D. Camacho, J. R. Rabuñal, M. Ojeda-Aciego, J. Medina, J. C. Riquelme, and A. Troncoso, Eds., Cham: Springer Nature Switzerland, 2024, pp. 121–130.
K. Zaman, T. Ahmed, M. A. Hanif, A. Marchisio, and M. Shafique, “A Comparative Analysis of Hybrid-Quantum Classical Neural Networks BT - Grid, Cloud, and Cluster Computing; Quantum Technologies; and Modeling, Simulation and Visualization Methods,” H. R. Arabnia, M. Takata, L. Deligiannidis, P. Rivas, M. Ohue, and N. Yasuo, Eds., Cham: Springer Nature Switzerland, 2025, pp. 102–115.
S. Markidis, “Programming Quantum Neural Networks on NISQ Systems: An Overview of Technologies and Methodologies,” 2023. doi: 10.3390/e25040694.
D. Guala, S. Zhang, E. Cruz, C. A. Riofrío, J. Klepsch, and J. M. Arrazola, “Practical overview of image classification with tensor-network quantum circuits,” Sci. Rep., vol. 13, no. 1, p. 4427, 2023, doi: 10.1038/s41598-023-30258-y.
P. Bhaskaran and S. Prasanna, “An Accuracy Analysis Of Classical And Quantum Machine Learning Algorithms Using Different Datasets,” in 2024 2nd International Conference on Networking and Communications (ICNWC), 2024, pp. 1–8. doi: 10.1109/ICNWC60771.2024.10537433.
I. Piatrenka and M. Rusek, “Quantum Variational Multi-class Classifier for the Iris Data Set BT - Computational Science – ICCS 2022,” D. Groen, C. de Mulatier, M. Paszynski, V. V Krzhizhanovskaya, J. J. Dongarra, and P. M. A. Sloot, Eds., Cham: Springer International Publishing, 2022, pp. 247–260.
H. Wang, “A novel feature selection method based on quantum support vector machine,” Phys. Scr., vol. 99, no. 5, p. 56006, 2024, doi: 10.1088/1402-4896/ad36ef.
