COMPARISON OF QUANTUM DEEP LEARNING METHODS FOR IMAGE CLASSIFICATION

Öz

Nowadays, with the discovery of the power and potential of quantum computers, developing and understanding quantum-based deep learning models has become an important research area. This study investigates Quantum Transfer Learning and Quantum Hybrid Learning models that involve feature extraction and training processes using Convolutional Neural Networks (CNN) and Vision Transformer (ViT). The study aims to explore the potential advantages and differences of quantum deep learning techniques. It is envisioned that quantum computing can provide significant advantages in terms of computational speed and efficiency, especially in complex and large-scale data sets. Therefore, this study will contribute to a better understanding of the practical applications and potential impacts of quantum deep learning techniques. In this study, we evaluate the performance of four different quantum deep learning architectures using two different datasets. The classifiers used are the pre-trained ResNet-50 with a kernel size of 5x5 and the state-of-the-art CaiT-24-XXS-224 (CaiT) transducers. Optimization was performed with Adam optimizer using the cross entropy loss function. A total of eight models were trained, each with ten iterations. Accuracy (Acc), balanced accuracy (BA), overall F𝛽 (F_beta) macro score F1 and F2, Matthew's Correlation Coefficient (MCC), sensitivity (Sens) and specificity (Spec) were used as performance measures.

Anahtar Kelimeler

• Quantum Transfer Learning
• Quantum Artificial Intelligence Models
• Hybrid Quantum-Classical Learning
• Vision Transformers

GÖRÜNTÜ SINIFLANDIRMADA KUANTUM DERİN ÖĞRENME YÖNTEMLERİNİN KARŞILAŞTIRILMASI

Öz

Günümüzde kuantum bilgisayarların gücü ve potansiyelinin keşfedilmesiyle birlikte, kuantum tabanlı derin öğrenme modelleri geliştirmek ve anlamak önemli bir araştırma alanı haline gelmiştir. Bu çalışma, Evrişimli Sinir Ağları (CNN) ve Vision Transformer (ViT) kullanılarak öznitelik çıkarımı ve eğitim süreçlerini içeren Kuantum Transfer Öğrenme ve Kuantum Hibrit Öğrenme modellerini incelemektedir. Çalışma, kuantum derin öğrenme tekniklerinin potansiyel avantajlarını ve farklılıklarını araştırmayı amaçlamaktadır. Kuantum hesaplamanın, özellikle karmaşık ve büyük ölçekli veri setlerinde hesaplama hızı ve verimlilik açısından önemli avantajlar sağlayabileceği öngörülmektedir. Dolayısıyla, bu çalışma, kuantum derin öğrenme tekniklerinin pratik uygulamalarının ve potansiyel etkilerinin daha iyi anlaşılmasına katkıda bulunacaktır. Bu çalışmada, iki farklı veri seti kullanılarak dört farklı kuantum derin öğrenme mimarisinin performansı değerlendirilmiştir. Kullanılan sınıflandırıcılar, önceden eğitilmiş 5x5 çekirdek boyutuna sahip ResNet-50 ve son teknoloji ürünü CaiT-24-XXS-224 (CaiT) dönüştürücüleridir. Optimizasyon, Adam optimizer ile çapraz entropi kayıp fonksiyonu kullanılarak gerçekleştirilmiştir. Her biri on tekrarlı olmak üzere toplam sekiz model eğitimi yapılmıştır. Performans ölçütleri olarak doğruluk (Acc), dengeli doğruluk (BA), genel F𝛽 makro skorundan F1 ve F2, Matthew's Korelasyon Katsayısı (MCC), duyarlılık (Sens) ve özgüllük (Spec) kullanılmıştır.

Anahtar Kelimeler

• Kuantum Transfer Öğrenme
• Kuantum Yapay Zeka Modelleri
• Hibrit Kuantum-Klasik Öğrenme
• Vision Transformers

Kaynakça

1. Amine Cherrat, I., Kerenidis, I., Mathur, N., et al. "Hybrid Quantum Vision Transformers for Event Classification in High Energy Physics." Quantum Journal, 2024.
2. Arthur, D., vd., 2022. A hybrid quantum-classical neural network architecture for binary classification. arXiv preprint arXiv:2201.01820.
3. Bağcı, S.A., Ekiz, H. ve Yılmaz, A., 2003. Determination of the salt tolerance of some barley genotypes and the characteristics affecting tolerance. Turkish Journal of Agriculture and Forestry, 27, 253-260. https://doi.org/xxx.xx./zzz.12345
4. Banchi, L., ve Crooks, G. E., 2021. Measuring analytic gradients of general quantum evolution with the stochastic parameter shift rule. Quantum, 5, 356.
5. Barenco, A., vd., 1995. Elementary gates for quantum computation. Physical Review A, 52(5), 3457–3467.
6. Benedetti, M., Lloyd, E., Sack, S., and Fiorentini, M. Parameterized quantum circuits as machine learning models. Quantum Science and Technology. 2019, vol. 4, no. 4, p. 043001. DOI: 10.1088/2058-9565/ab4eb5
7. Bharti, K., et al. "Noisy intermediate-scale quantum algorithms." Reviews of Modern Physics, vol. 94, no. 1, 2022, p. 015004.
8. Cerezo, M., et al. "Variational quantum algorithms." Nature Reviews Physics, vol. 3, no. 9, 2021, pp. 625-644.

9. Carion, N., Massa, F., Synnaeve, G., Usunier, N., Girshick, R., ve Guizilini, V., 2020. End-to-end object detection with transformers. In European Conference on Computer Vision, 213-229. Springer, Cham.
10. Cong, I., Choi, S., ve Lukin, M. D., 2019. Quantum convolutional neural networks. Nature Physics, 15, 1273-1278.
11. Cross, A., 2018. The IBM Q experience and QISKit open-source quantum computing software. APS March Meeting Abstracts, L58.003.
12. Datta, A., Flammia, S. T., ve Caves, C. M., 2005. Entanglement and the power of one qubit. Physical Review A, 72(4), 042316.
13. Dhara, B., Agrawal, M., ve Roy, S. D., 2024. Multi-class classification using quantum transfer learning. Quantum Information Processing, 23, 34.
14. DiVincenzo, D. P., 1998. Quantum gates and circuits. Proceedings of the Royal Society of London. Series A: Mathematical, Physical and Engineering Sciences, 454(1969), 261-276.
15. Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zisserman, A., ve Houlsby, N., 2021. An image is worth 16x16 words: Transformers for image recognition at scale. ICLR.
16. Farhi, E., Goldstone, J., ve Gutmann, S., 2014. A quantum approximate optimization algorithm. arXiv preprint arXiv:1411.4028.
17. Fredkin, E., ve Toffoli, T., 1982. Conservative logic. International Journal of Theoretical Physics, 21(3-4), 219–253.
18. Garg, S., ve Ramakrishnan, G., 2020. Advances in quantum deep learning: An overview. arXiv preprint arXiv:2005.04316.
19. Han, K., Xiao, A., Wu, E., Guo, J., Wang, C., ve Dai, J., 2022. Survey: Transformer based image segmentation using self-attention mechanism. Expert Systems with Applications, 195, 116580.
20. Henderson, M., Shakya, S., Pradhan, S., ve Cook, T., 2020. Quanvolutional neural networks: Powering image recognition with quantum circuits. Quantum Machine Intelligence, 2(2).
21. Kaggle, 2017. Medical MNIST. https://www.kaggle.com/datasets/andrewmvd/medical-mnist
22. Kaggle, 2018. Dogs vs Cats. https://www.kaggle.com/datasets/salader/dogs-vs-cats
23. Kerenidis, I., Landman, J., ve Prakash, A., 2019. Quantum algorithms for deep convolutional neural networks. arXiv preprint arXiv:1911.01117.
24. Khan, S., Naseer, M., Hayat, M., Zamir, S. W., Khan, F. S., ve Shah, M., 2022. Transformers in vision: A survey. ACM Computing Surveys (CSUR), 55(1), 1-41.
25. Khoshaman, A., vd., 2018. Quantum variational autoencoder. Quantum Science and Technology, 4(1), 014001.
26. Kockum, A. K., 2014. Quantum optics with artificial atoms. Chalmers University of Technology: Gothenburg, Sweden.
27. LeCun, Y., Bottou, L., Bengio, Y., and Haffner, P. Gradient-based learning applied to document recognition. Proceedings of the IEEE. 1998, vol. 86, no. 11, pp. 2278–2324. DOI: 10.1109/5.726791.
28. LEE, Albert; KIM, Sun. Quantum gates and rotational operations in machine learning. Quantum Information Processing, 2020, 12(7): 98-104.
29. Liu, J., vd., 2021. Hybrid quantum-classical convolutional neural networks. Science China Physics, Mechanics & Astronomy, 64(9), 290311.
30. McClean, J. R., et al. "OpenFermion: The electronic structure package for quantum computers." Quantum Science and Technology, vol. 5, no. 3, 2020, p. 034014.
31. Mari, A., vd., 2020. Transfer learning in hybrid classical-quantum neural networks. Quantum, 4, 340.
32. Mishra, B., ve Samanta, A., 2022. Quantum Transfer Learning Approach for Deepfake Detection. Sparklinglight Transactions on Artificial Intelligence and Quantum Computing (STAIQC), 2(1), 17-27.
33. Mogalapalli, H., vd., 2022. Classical–quantum transfer learning for image classification. SN Computer Science, 3(1), 20.
34. Noble, W. S., 2006. What is a support vector machine? Nature Biotechnology, 24(12), 1565-1567.
35. Panda, S.K. ve Choudhury, S., 2005. Chromium stress in plants. Brazilian Journal of Plant Physiology, 17, 95–102. https://doi.org/xxx.xx./zzz.12345
36. PATEL, Raj; SHARMA, Meena. Entanglement in quantum networks: Applications and gate constructions. Quantum Engineering, 2021, 9(1): 34-42.
37. PennyLane, Kasım 2022. Quantum transfer learning. https://pennylane.ai/qml/demos/tutorial_quantum_transfer_learning.html
38. Preskill, John. "Quantum computing in the NISQ era and beyond." Quantum, vol. 2, 2018, p. 79.
39. Qi, J., ve Tejedor, J., 2022. Classical-to-quantum transfer learning for spoken command recognition based on quantum neural networks. In ICASSP 2022-2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 8627-8631. IEEE.
40. Qiskit, Ekim 2022. Machine Learning with Qiskit. https://qiskit.org/textbook/ch-machine-learning/machine-learning-qiskit-pytorch.html
41. Rebentrost, P., Mohseni, M., ve Lloyd, S., 2014. Quantum support vector machine for big data classification. Physical Review Letters, 113(13), 130503.
42. Romero, J., Olson, J. P., ve Aspuru-Guzik, A., 2017. Quantum autoencoders for efficient compression of quantum data. Quantum Science and Technology, 2(4), 045001.
43. Samantaray, S., 2002. Biochemical responses of Cr–tolerant and Cr–Sensitive mung bean cultivars grown on varying levels of chromium. Chemosphere, 47, 1065–1072. https://doi.org/xxx.xx./zzz.12345
44. Sarkar, S. "Quantum Transfer Learning for MNIST Classification Using a Hybrid Quantum-Classical Approach." arXiv, 2024.
45. Schuld, M., Sinayskiy, I., and Petruccione, F. Quantum machine learning: A classical perspective. Contemporary Physics. 2019, vol. 60, no. 2, pp. 172–185. DOI: 10.1080/00107514.2018.1457518.
46. Schumacher, B., 1995. Quantum coding. Physical Review A, 51(4), 2738.
47. Shor, P. W., 2002. Introduction to quantum algorithms. Proceedings of Symposia in Applied Mathematics, 143-160.
48. Shepherd, D. J., 2006. On the Role of Hadamard Gates in Quantum Circuits. Quantum Information Processing, 5, 161-177.
49. SMITH, John; DOE, Jane. Hadamard gates and quantum computing algorithms. Journal of Quantum Computing, 2019, 15(3): 245-250.
50. Steiner, A., Kolesnikov, A., Zhai, X., Wightman, R., Uszkoreit, J., ve Beyer, L., 2021. How to train your ViT? Data, augmentation, and regularization in vision transformers. arXiv preprint arXiv:2106.10270.
51. Taylor, R. D. Quantum Technology Development, Policy and Governance in the US.
52. Toffoli, T., 1980. Reversible computing. In International Colloquium on Automata, Languages, and Programming, 632–644. Springer, Berlin/Heidelberg, Germany.
53. Toğaçar, M., 2021. X-ışınlı Göğüs İmgelerini Kullanarak Solunum Yolu Hastalıklarının Tespitinde Kuantum Transfer Öğrenme Modelinin Rolü. Düzce Üniversitesi Bilim ve Teknoloji Dergisi, 9(5), 1754-1765.
54. WANG, Li; YANG, Wei. Quantum entanglement and its role in machine learning models. International Journal of Quantum Information, 2020, 18(6): 150-162.
55. Yan, J., Liu, P., Gu, X., et al. "Remote Sensing Image Scene Classification in Hybrid Classical–Quantum Transfer Learning CNN with Small Samples." Sensors, 23(18), 2023.
56. Yang, J., vd., 2023. MedMNIST v2-A large-scale lightweight benchmark for 2D and 3D biomedical image classification. Scientific Data, 10(1), 41.
57. ZHU, Jing; HUANG, Zhen; KAIS, Sabre. 2009. Simulated quantum computation of global minima. Molecular Physics, 107(19), 2015-2023.