Quantum Convolution Neural Network
Keywords:quantum computer, quantum method of support vectors, quantum convolutional neural network, quantum computing, classification, machine learning
In this work, quantum convolutional neural networks are considered in the task of recognizing handwritten digits. A proprietary quantum scheme for the convolutional layer of a quantum convolutional neural network is proposed. A proprietary quantum scheme for the pooling layer of a quantum convolutional neural network is proposed. The results of learning quantum convolutional neural networks are analyzed. The built models were compared and the best one was selected based on the accuracy, recall, precision and f1-score metrics. A comparative analysis was made with the classic convolutional neural network based on accuracy, recall, precision and f1-score metrics. The object of the study is the task of recognizing numbers. The subject of research is convolutional neural network, quantum convolutional neural network. The result of this work can be applied in the further research of quantum computing in the tasks of artificial intelligence.
Guillaume Verdon, Mochael Broughton, Jacob Biamonte, “A quantum algorithm to train neural networks using low-depth circuits”, arXiv.org [Electronic resource]. URL: https://arxiv.org/abs/1712.05304 (date of the application: 10.08.2019)
Maria Schuld, Alex Bocharov, Krysta Svore, Nathan Wiebe. Circuit-centric quantum classifiers. arXiv preprint arXiv:1804.00633, 2018.
Metodi i modeli intellektual'nogo analiza dannykh. Praktikum [Yelektronniy resurs]: navchal'nyy posibnik dlya studentov, yaki navchayut'sya za spetsial'nistyu 122 «Komp'yuterní nauki», osvitn'oí̈ programmy «Sistemy i metody shtuchnogo intelektu» / N. I. Nedashkovskaya; KPI im. Igor' Sikors'kogo. – Elektronnyye teksty dani (1 fayl: 1,77 Mbayt). – Kyiv: KPI im. Igor' Sikors'kogo, 2019, 71 s. https://ela.kpi.ua/handle/123456789/53764 [in Ukrainian]
Kvantova realizatsiya klassifikatora metodov opornykh vektorov (SVM): diplom robota opornogo ... bakalavra : 122 Komp'yuternyye nauki / Chinnik Petro Anatoliyovich, Kyiv, 2021, 97 s. [in Ukrainian]
Tak Hur, Leeseok Kim, and Daniel K. Park. “Quantum convolutional neural network for classical data classification”, arXiv.org [Electronic resource]. URL: https://arxiv.org/pdf/2108.00661.pdf (date of the application 2 August 2021)
Edward Grant, Marcello Benedetti, Shuxiang Cao, Andrew Hallam, Joshua Lockhart, Vid Stojevic, Andrew G. Green, and Simone Severini. Hierarchical quantum classifiers. npj Quantum Information, 4(1):65, 2018 https://doi.org/10.1038/s41534-018-0116-9
Robert M. Parrish, Edward G. Hohenstein, Peter L. McMahon, and Todd J. Martı́nez. Quantum computation of electronic transitions using a variational quantum eigensolver. Phys. Rev. Lett., 122:230401, 2019. https://doi.org/10.1103/PhysRevLett.122.230401
Sukin Sim, Peter D. Johnson, and Alán Aspuru-Guzik. Expressibility and entangling capability of parameterized quantum circuits for hybrid quantum-classical algorithms. Advanced Quantum Technologies, 2(12):1900070. 2019. https://doi.org/10.1002/qute.201900070
Martín Larocca, Nathan Ju, Diego García-Martín, Patrick J. Coles, Marco Cerezo, “Theory of overparametrization in quantum neural networks” [Electronic resource]. nature.org URL: https://www.nature.com/articles/s43588-023-00467-6 (date of the application 26 June 2023) https://doi.org/10.1038/s43588-023-00467-6
Authors who publish with this journal agree to the following terms:
Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).