2025, issue 1, p. 106-117
Received 09.01.2025; Revised 11.02.2025; Accepted 25.03.2025
Published 28.03.2025; First Online 30.03.2025
https://doi.org/10.34229/2707-451X.25.1.11
Previous | FULL TEXT (in Ukrainian) | Next
Quantum Variational Autoencoder Based on Weak Measurements With Fuzzy Filtering of Input Data
Vyacheslav Korolyov *
, Maksim Ogurtsov , Oleksandr Khodsinskyi
V.M. Glushkov Institute of Cybernetics of the NAS of Ukraine, Kyiv
* Correspondence: This email address is being protected from spambots. You need JavaScript enabled to view it.
Introduction. The development of quantum computing and artificial intelligence necessitates the development of hybrid quantum-classical algorithms for solving complex computational problems. The relevance of the research is due to the need for new approaches to making creative AI decisions in conditions of exhaustion of training samples. (QVA) based on weak measurements with fuzzy filtering of input data is a promising research direction.
The article first proposes a quantum variational autoencoder (QVA) based on weak measurements, which expands the space of possible solutions due to quantum effects – qubit entanglement, superposition of states and information teleportation. A fundamentally important modification is the introduction of weak measurements, which provide information about the quantum system with minimal impact on its state.
The purpose of the article is to improve AI through modeling of autoencoder algorithms using weak measurements and fuzzy logic.
Results. For the first time, numerical simulation of KVA based on weak measurements with fuzzy filtering was performed on classical computers and cloud services. The quality of KVA reconstruction is comparable to classical autoencoders. The simulation was performed for a one-dimensional signal, since for the CIFAR-10 and MNIST training samples, the simulation requires more than 5 petabytes of RAM. The KVA runtime in Google Colab was approximately 40 seconds.
Conclusions. The integration of the fuzzy filtering mechanism into the KVA structure expands the capabilities of processing distorted and incomplete data. Such a modification increases the model's resistance to thermal noise and input data artifacts, improving the quality of information compression. Fuzzy clustering allows the system to effectively operate with ambiguous situations under conditions of uncertainty.
Computer simulations have shown that adapting the fuzzy membership function to the type of input data, increasing the number of latent variables, and selecting the learning rate of the neural network can improve the quality of the reconstruction of the input signal.
Keywords: quantum computing, neural network, variational autoencoder, fuzzy logic, weak measurements.
Cite as: Korolyov V., Ogurtsov M., Khodsinskyi O. Quantum Variational Autoencoder Based on Weak Measurements With Fuzzy Filtering of Input Data. Cybernetics and Computer Technologies. 2025. 1. P. 106–117. (in Ukrainian) https://doi.org/10.34229/2707-451X.25.1.11
1. O'brien J.L. Optical quantum computing. Science. 2007. 318 (5856): 1567–1570. https://doi.org/10.1126/science.1142892
2. Sunstein C.R. The AI Calculation Debate. Available at SSRN 5054402. 2024. Dec 13. https://doi.org/10.2139/ssrn.5054402
3. Khoshaman A., Vinci W., Denis B., Andriyash E., Sadeghi H., Amin M.H. Quantum variational autoencoder. Quantum Science and Technology. 2018. 4 (1): 014001. https://doi.org/10.1088/2058-9565/aada1f
4. Aharonov Ya., Pan Y., Karimi E. et al. Weak measurements and quantum-to-classical transitions in free electron–photon interactions. Light Sci. Appl. 2023. 12 (267). https://doi.org/10.1038/s41377-023-01292-2
5. Matzkin A. Weak Values and Quantum Properties. Found. Phys. 2019. 49. P. 298–316. https://doi.org/10.1007/s10701-019-00245-3
6. Kastner R.E. Demystifying Weak Measurements. Found. Phys. 2017. 47. P. 697–707. https://doi.org/10.1007/s10701-017-0085-4
7. Cohen E. What Weak Measurements and Weak Values Really Mean: Reply to Kastner. Found. Phys. 2017. 47. P. 1261–1266. https://doi.org/10.1007/s10701-017-0107-2
8. Ruelas D., Uria M., Massoni E., Zela F. Testing precision and accuracy of weak value measurements in an IBM quantum system. AVS Quantum Sci. 2024. 6 (015001). https://doi.org/10.1116/5.0184965
9. Mujal P., Martínez-Peña R., Giorgi G.L. et al. Time-series quantum reservoir computing with weak and projective measurements. npj Quantum Inf. 2023. 9 (16). https://doi.org/10.1038/s41534-023-00682-z
10. Lund A.P. Efficient quantum computing with weak measurements. New J. Phys. 2011. 13 (053024). https://doi.org/10.1088/1367-2630/13/5/053024
11. Pan Y., Zhang J., Cohen E. et al. Weak-to-strong transition of quantum measurement in a trapped-ion system. Nat. Phys. 2020. 16. P. 1206–1210. https://doi.org/10.1038/s41567-020-0973-y
12. White T., Mutus J., Dressel J. et al. Preserving entanglement during weak measurement demonstrated with a violation of the Bell–Leggett–Garg inequality. npj Quantum Inf. 2016. 2 (15022). https://doi.org/10.1038/npjqi.2015.22
13. Kim Y.S., Lee J.C., Kwon O. et al. Protecting entanglement from decoherence using weak measurement and quantum measurement reversal. Nature Phys. 2012. 8. P. 117–120. https://doi.org/10.1038/nphys2178
14. Man Zh., Xia Yu., An N. B. Manipulating entanglement of two qubits in a common environment by means of weak measurements and quantum measurement reversals. Phys. Rev. A. 2012. 86 (012325). https://doi.org/10.1103/PhysRevA.86.012325
15. Gillett G.G., Dalton R.B., Lanyon B.P. et al. Experimental Feedback Control of Quantum Systems Using Weak Measurements. Phys. Rev. Lett. 2010. 104 (080503). https://doi.org/10.1103/PhysRevLett.104.080503
16. Kim Y.S., Cho Y.W., Ra Y.S., Kim Y.H. Reversing the weak quantum measurement for a photonic qubit. Optics Express. 2009. 17 (14). P. 11978–11985. https://doi.org/10.1364/OE.17.011978
17. Murch K.W., Rajamani V., Siddiqi I. Weak Measurement and Feedback in Superconducting Quantum Circuits. In: Hadfield R., Johansson G. (eds) Superconducting Devices in Quantum Optics. Quantum Science and Technology. Springer, Cham. 2016. https://doi.org/10.1007/978-3-319-24091-6_7
18. Hulianitskyi L.F., Korolyov V.Yu., Khodzinskyi O.M. An Overview of Algorithms for Solving Vehicle Routing Problems in the Quantum-Classical Cloud. Cybernetics and Computer Technologies. 2023. 2. P. 23–31. https://doi.org/10.34229/2707-451X.23.2.3
19. Korolyov V.Yu., Khodzinskyi O.M. A Research of the Influence of Quantum Annealing Parameters on the Quality of the Solution of the Number Factorization Problem. Cybernetics and Computer Technologies. 2023. 1. P. 13–22. https://doi.org/10.34229/2707-451X.23.1.2
20. Hulianytskyi L.F., Korolyov V.Yu., Khodzinskyi O.M. Solving the Problem of Vehicle Routing on Modern Quantum-Classical Cloud Services. Selected Papers of the VIII International Scientific Conference “Information Technology and Implementation" (IT&I-2021). Conference Proceedings, Kyiv, Ukraine, December 01–03, 2021. P. 281–289. https://ceur-ws.org/Vol-3132/Short_9.pdf (accessed: 07.01.2024)
21. Korolyov V.Yu., Khodzinskyi O.M. Solving combinatorial optimization problems on quantum computers. Cybernetics and Computer Technologies. 2020. 2. P. 5–13. https://doi.org/10.34229/2707-451X.20.2.1
22. Johansson J.R., Nation P.D., Nori F. QuTiP: An open-source Python framework for the dynamics of open quantum systems. Computer physics communications. 2012. 183 (8):1760–72. https://doi.org/10.1016/j.cpc.2012.02.021
23. Korolyov V.Yu., Ogurtsov M.I., Khodzinskyi O.M. The problem of routing interbank financial obligations. Physical and mathematical modeling and information technologies. 36. P. 121–125. https://doi.org/10.15407/fmmit2023.36.121 (accessed: 07.01.2024)
24. Ogurtsov M.I. Review of Neural Networks Application in UAV Routing Problems. Selected Papers of the VIII Internat. Scien. Conf. “Information Technology and Implementation" (IT&I-2021). Workshop Proceedings. Kyiv, Ukraine, December 1–3, 2021. P. 45–54. https://ceur-ws.org/Vol-3179/Paper_5.pdf (accessed: 07.01.2024)
25. Korolyov V.Yu., Ogurtsov M.I. Statement of the Problem of Complete Set of UAV Group on the Basis of Models of Granular Calculations and Fuzzy Logic. Cybernetics and Computer Technologies. 2021. 2. P. 25–38. https://doi.org/10.34229/2707-451X.21.2.3
26. Goodfellow I., Bengio Yo. Deep Learning (Adaptive Computation and Machine Learning series). The MIT Press. 2016. 800 p. ISBN 0262035618.
27. Kingma D.P., Welling M. An Introduction to Variational Autoencoders. Now Publishers. 2019. 102 p. ISBN 1680836226. https://doi.org/10.1561/9781680836233
28. Amin M.H., Andriyash E., Rolfe J., Kulchytskyy B., Melko R. Quantum boltzmann machine. Physical Review X. 2018. 8 (2): 021050. https://doi.org/10.1103/PhysRevX.8.021050
29. Austin B.M., Zubarev D.Y., Lester Jr.W.A. Quantum Monte Carlo and related approaches. Chemical reviews. 2012. 112 (1). 263–288. https://doi.org/10.1021/cr2001564
30. Abouelnaga Y., Ali O.S., Rady H., Moustafa M. Cifar-10: Knn-based ensemble of classifiers. In2016 International Conference on Computational Science and Computational Intelligence (CSCI) 2016 Dec 15. P. 1192–1195. https://doi.org/10.1109/CSCI.2016.0225
31. Broughton M., Verdon G., McCourt T., Martinez A.J., Yoo J.H., Isakov S.V., Massey P., Halavati R., Niu M.Y., Zlokapa A., Peters E. Tensorflow quantum: A software framework for quantum machine learning. arXiv preprint arXiv:2003.02989. 2020 Mar 6.
32. Code examples for article. https://github.com/novice108/quant_weak_measur_autoencoder (access 07.01.2024)
ISSN 2707-451X (Online)
ISSN 2707-4501 (Print)
Previous | FULL TEXT (in Ukrainian) | Next