QUANTUM DEEP LEARNING OF CONVOLUTIONAL NEURAL NETWORK USING VARIATIONAL QUANTUM CIRCUIT
Abstract
Quantum computing in general and quantum deep learning represent a promising field related
to the research of modern methods and algorithms of quantum computing used for the purpose
of teaching and developing new architectures of artificial neural networks. Recently, there
has been a trend that research conducted in the field of quantum deep learning is becoming increasingly
widespread among specialists. This can be explained by the fact that it has been established
that quantum circuits are capable of functioning like artificial neural networks, while
demonstrating the best results in solving several tasks, including, for example, the actual task of
classifying objects in an image or in a video stream. Thanks to the rapid development of quantum
computing in the field of deep learning, optimal solutions have been found for such urgent problems
as the vanishing gradient problem, finding a local minimum, improving the efficiency of
large-scale parametric machine learning algorithms, eliminating decoherence and quantum errors,
etc. Within the framework of this work, the process of functioning of a quantum variational
scheme is described, its main characteristics are established, and disadvantages are identified.
The key features of quantum computing, on which the process of implementing quantum deep
learning with the reinforcement of a convolutional neural network is based, are also analyzed. In
addition, quantum deep learning of a convolutional neural network has been carried out using a
variational quantum scheme, which leads to an increase in the performance of a convolutional
neural network in solving the problem of image processing, namely its classification, using a
quantum computing environment. The relevance of this article consists in the implementation of a
quantum deep learning algorithm with the reinforcement of a convolutional neural network for
image processing, as well as the great importance of the subject of this study for the future development
of quantum computing devices that can be used in artificial intelligence systems, etc.,
which corresponds to the priority direction of the development of domestic science.
References
efficient and distributed learning over wireless networks: Principles and applications,
Proceedings of the IEEE, May 2021, Vol. 109, No. 5, pp. 796-819.
2. Choi J., Oh S., and Kim J. Energy-efficient cluster head selection via quantum approximate
optimization, Electronics, 2020, Vol. 9, No. 10.
3. Cong I., Choi S., and. Lukin M.D. Quantum convolutional neural networks, Nature Physics,
2019, Vol. 15, No. 12, pp. 1273-1278.
4. Preskill J. Quantum computing in the nisq era and beyond, Quantum, 2018, Vol. 2, pp. 79.
5. Oh S., Choi J., and Kim J. A tutorial on quantum convolutional neural networks (QCNN), in Proceedings
of the IEEE International Conference on Information and Communication Technology Convergence
(ICTC), 2020, pp. 236-239.
6. Gushanskiy S.M., Kozlovskiy A.V., Buglov V.E. Kvantovaya obrabotka izobrazheniy [Quantum image
processing], Tekhnologii razrabotki informatsionnykh sistem TRIS-2019: Mater. IX Mezhdunarodnoy
nauchno-tekhnicheskoy konferentsii [Technologies for the development of information systems
TRIS-2019: Materials of the IX International Scientific and Technical Conference]. Gelendzhik: Izdvo
YuFU, 2019, pp. 217-222.
7. Gushanskiy S.M., Buglov V.E., Podoroga E.A. Analiz protsessov obucheniya i ispol'zovaniya
kvantovykh neyronnykh setey [Analysis of learning processes and the use of quantum neural networks],
Nauka, tekhnologii, obshchestvo – NTO-2021: Sb. nauchnykh statey po materialam
Vserossiyskoy nauchnoy konferentsii [Science, technology, society - NTO-2021: Collection of scientific
articles based on the materials of the All-Russian Scientific Conference]. Krasnoyarsk: Izd-vo
obshchestvennogo uchrezhdeniya «Krasnoyarskiy kraevoy Dom nauki i tekhniki Rossiyskogo soyuza
nauchnykh i inzhenernykh obshchestvennykh ob"edineniy», 2021, pp. 29-34.
8. Gushanskiy S.M., Gorbunov A.V., Pereverzev V.A. Primenimost' kvantovykh neyronnykh setey dlya
zadach raspoznavaniya i obnaruzheniya obrazov [Applicability of quantum neural networks for
pattern recognition and detection problems], Vestnik Adygeyskogo gosudarstvennogo universiteta
[Bulletin of the Adygea State University], pp. 59-68.
9. Chen S.Y.-C., Yang C.-H.H., Qi J., Chen P.-Y., Ma X., and Goan H.-S. Variational quantum
circuits for deep reinforcement learning, IEEE Access, 2020, Vol. 8, pp. 141007-141024.
10. Garg S. and Ramakrishnan G. Advances in quantum deep learning: An overview, arXiv preprint
arXiv:2005.04316, 2020.
11. Bausch J. Recurrent quantum neural networks, Advances in Neural Information Processing
Systems, 2020, Vol. 33.
12. Guzik V.F., Gushanskiy S.M., Potapov V.S. Razrabotka i issledovanie kvantovykh mode-ley
preobrazovaniya izobrazheniy [Development and research of quantum models of image transformation],
Tr. uchebnykh zavedeniy svyazi [Proceedings of educational institutions of communication].
Founders: St. Petersburg State University of Telecommunications named after Prof.
M.A. Bonch-Bruevich, 2021, pp. 20-30.
13. Gushanskiy S.M., Potapov V.S. Realizatsiya kvantovogo algoritma obnaruzheniya granits ob"ektov i
kraev izobrazheniya [Implementation of a quantum algorithm for detecting object boundaries and image
edges], Inzhenernyy vestnik Dona [Engineering Bulletin of the Don]. Founders: Rostov regional
branch of the All-Russian public organization "Russian Engineering Academy", 2021, pp. 204-209.
14. Altayskiy M.V., Kaputkina N.E., Krylov V.A. Kvantovye neyronnye seti: sovremennoe sostoyanie i
perspektivy razvitiya [Quantum neural networks: current state and prospects of development],
Fizika elementarnykh chastits i atomnogo yadra [Physics of elementary particles and atomic nucleus],
2014, Vol. 45, Issue 5-6, pp. 1-43.
15. Gushanskiy S.M., Guzik V.F., Lyapuntsova E.V. Kvantovyy komp'yuting: ucheb. posobie [Quantum
computing: a textbook]. Taganrog: Izd-vo YuFU, 2012, 120 p.
16. Alchieri L., Badalotti D., Bonardi P., Bianco S. An introduction to quantum machine learning:
from quantum logic to quantum deep learning, Quantum Machine Intelligence, 2021, Part 3
(Scopus).
17. Potapov V., Gushansky S, Samoylov A., Polenov M. The Quantum Computer Model Structure
and Estimation of the Quantum Algorithms Complexity, Computational Methods in Systems and
Software 2018 (CoMeSySo 2018), September 2018: Proceedings Advances in Intelligent Systems
and Computing. Vol. 859. Springer Nature Switzerland AG, 2019 pp. 307-315. (Scopus; Warsaw,
Poland).
18. SkillFactory. Realizuem i sravnivaem optimizatory modeley v glubokom obuchenii [SkillFactory.
We implement and compare model optimizers in deep learning]. Available at:
https://habr.com/ru/company/skillfactory/blog/525214/ (accessed 29 November 2021).
19. Kryzhanovskiy A.V, Gushanskiy S.M. Issledovanie kvantovykh algoritmov obnaruzheniya i
raspoznavaniya lits s pomoshch'yu kvantovoy neyroseti [Investigation of quantum algorithms for face
detection and recognition using a quantum neural network], Fundamental'nye i prikladnye aspekty
komp'yuternykh tekhnologiy i informatsionnoy bezopasnosti: Mater. VII Vserossiyskoy nauchnotekhnicheskoy
konferentsii [Fundamental and applied aspects of computer technology and information
security: Materials of the VII All-Russian Scientific and Technical Conference]. Taganrog:
Izd-vo YuFU, 2021, pp. 346-349.
20. Dunjko V. and Briegel H.J. Machine learning & artificial intelligence in the quantum domain:
A review of recent progress, Rep. Prog. Phys., June 2018, Vol. 81, pp. 074001
