Abstract
Quantum system attributes, notably entanglement, are indispensable in manipulating quantum information tasks. Ergo, machine learning applications to help harness the sophistication of quantum information theory have surged. However, relying on unsuited prototypes and not bridling quantum information data for usual processors has often resulted in sub-optimal efficaciousness and inconvenience. We develop a custom deep convolutional neural network, XpookyNet, which is streamlined with respect to the interrelationships of density matrices of two-qubit systems to underpin three-qubit systems, breaking new ground to more qubit systems by their subsystems. Comparative implementation of XpookyNet provides instantaneous and meticulous results with an accuracy of 98.53% in merely a few epochs. XpookyNet effectively handles the inherent complexity of quantum information, equipping deeper insights into many-body systems as a bedrock. The study also investigates quantum features and their relation to the purity of a density matrix directly related to noise and system decoherence in NISQ-era quantum computation. Preparing the density matrix in a compact and compatible format with customary convolutional neural networks plays a determining role in dissecting quantum features. The procedure renders a convex criterion that detects entanglement and is a yardstick for quantum system coherence.
Similar content being viewed by others
Explore related subjects
Discover the latest articles, news and stories from top researchers in related subjects.Data Availability
The data associated with this project is available on GitHub. You can access the repository, which includes all relevant datasets, code, and documentation, at the following link: https://github.com/AKookani/XpookyNet
Code Availability
The codes that support the plots within the paper are publicly available on https://github.com/AKookani/XpookyNet
References
Ahmed S, Muñoz CS, Nori F, Kockum AF (2020) Classification and reconstruction of optical quantum states with deep neural networks. arXiv:2012.02185
Arkhipov II, Barasiński A, Svozilík J (2018) Negativity volume of the generalized Wigner function as an entanglement witness for hybrid bipartite states. Sci Rep 8(1):16955
Asif N, Khalid U, Khan A, Duong TQ, Shin H (2023) Entanglement detection with artificial neural networks. Sci Rep 13(1):1562
Baccari F, Cavalcanti D, Wittek P, Acín A (2017) Efficient device-independent entanglement detection for multipartite systems. Phys Rev X 7:021042. https://doi.org/10.1103/PhysRevX.7.021042
Bai Y-K, Xu Y-F, Wang ZD (2014) General monogamy relation for the entanglement of formation in multiqubit systems. Phys Rev Lett 113(10):100503. https://doi.org/10.1103/PhysRevLett.113.100503
Bhaskara VS, Panigrahi P (2016) Generalized concurrence measure for faithful quantification of multiparticle pure state entanglement using Lagrange’s identity and wedge product. Quantum Inf Process 16:1–15. https://doi.org/10.1007/s11128-017-1568-0
Blasiak P, Markiewicz M (2019) Entangling three qubits without ever touching. Sci Rep 9(1):20131
Chalumuri A, Kune R, Manoj BS (2021) A hybrid classical-quantum approach for multi-class classification. Quantum Inf Process 20(3). https://doi.org/10.1007/s11128-021-03029-9
Chen Y, Pan Y, Zhang G, Cheng S (2021) Detecting quantum entanglement with unsupervised learning. Quantum Sci Technol 7(1):015005
Chollet F (2021) Deep learning with Python. Simon and Schuster
Das T, Karczewski M, Mandarino A, Markiewicz M, Woloncewicz B, Żukowski M (2022) Comment on ‘single particle nonlocality with completely independent reference states’. New J Phys 24(3):038001
Díez-Valle P, Porras D, García-Ripoll JJ (2021) Quantum variational optimization: the role of entanglement and problem hardness. Phys Rev A 104(6):062426. https://doi.org/10.1103/PhysRevA.104.062426
Essakhi M, Khedif Y, Mansour M, Daoud M (2022) Intrinsic decoherence effects on quantum correlations dynamics. Opt Quantum Electron 54:1–15
Facchi P, Parisi G, Pascazio S, Scardicchio A, Yuasa K (2019) Phase diagram of bipartite entanglement. J Phys A Math Theor 52. https://doi.org/10.1088/1751-8121/ab3f4e
Fadel M, Ares L, Luis A, He Q (2020) Number-phase entanglement and Einstein-Podolsky-Rosen steering. Phys Rev A 101:052117. https://doi.org/10.1103/PhysRevA.101.052117
Fanizza M, Skotiniotis M, Calsamiglia J, Muñoz-Tapia R, Sentís G (2022) Universal algorithms for quantum data learning. Europhysics Lett. https://doi.org/10.1209/0295-5075/ac9c29
Girardin A, Brunner N, Kriváchy T (2022) Building separable approximations for quantum states via neural networks. Phys Rev Res 4(2):023238
Givi ZS, Jaber M, Neumann W (2015) Modelling worker reliability with learning and fatigue. Appl Math Model 39:5186–5199. https://doi.org/10.1016/J.APM.2015.03.038
Gu X, Chen L, Zeilinger A, Krenn M (2019) Quantum experiments and graphs. III. High-dimensional and multiparticle entanglement. Phys Rev A 99(3):032338
Harney C, Paternostro M, Pirandola S (2021) Mixed state entanglement classification using artificial neural networks. New J Phys 23(6):063033
Huber M, Lami L, Lancien C, Müller-Hermes A (2018) High-dimensional entanglement in states with positive partial transposition. Phys Rev Lett 121(20):200503. https://doi.org/10.1103/PhysRevLett.121.200503
Hyllus P, Eisert J (2006) Optimal entanglement witnesses for continuous-variable systems. New J Phys 8(4):51
Jia L, Gaüzère B, Honeine P (2022) Graph kernels based on linear patterns: theoretical and experimental comparisons. Expert Syst Appl 189:116095
Johansson JR, Nation PD, Nori F (2013) QuTiP 2: a Python framework for the dynamics of open quantum systems. Comput Phys Commun 184:1234. https://doi.org/10.1016/j.cpc.2012.11.019
Kim JS (2021) Entanglement of formation and monogamy of multi-party quantum entanglement. Sci Rep 11:1. https://doi.org/10.1038/s41598-021-82052-3
Kookani A (2022) Quantangle. Kaggle. https://doi.org/10.34740/KAGGLE/DSV/3663663. https://www.kaggle.com/dsv/3663663
Laloë F (2019) Do we really understand quantum mechanics?, pp 189–222. https://doi.org/10.1017/9781108569361.010. Cambridge University Press, Cambridge
Lan R, Zou H, Pang C, Zhong Y, Liu Z, Luo X (2019) Image denoising via deep residual convolutional neural networks. Signal, Image Vid Process 15:1–8. https://doi.org/10.1007/S11760-019-01537-X
Lanyon B, Maier C, Holzapfel M, Baumgratz T, Hempel C, Jurcevic P, Dhand I, Buyskikh A, Daley A, Cramer M, Plenio M, Blatt R, Roos C (2016) Efficient tomography of a quantum many-body system. Nat Phys 13:1158–1162. https://doi.org/10.1038/nphys4244
Li Z, Liu F, Yang W, Peng S, Zhou J (2020) A survey of convolutional neural networks: analysis, applications, and prospects. IEEE Trans Neural Netw Learn Syst 33:6999–7019. https://doi.org/10.1109/TNNLS.2021.3084827
Liu J-J, Hou Q, Cheng M-M, Wang C, Feng J (2020) Improving convolutional networks with self-calibrated convolutions. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pp 10096–10105
Liu Z, Tang Y, Dai H, Liu P, Chen S, Ma X (2022) Detecting entanglement in quantum many-body systems via permutation moments. Phys Rev Lett 129:260501. https://doi.org/10.1103/PhysRevLett.129.260501
Lu S, Huang S, Li K, Li J, Chen J, Lu D, Ji Z, Shen Y, Zhou D, Zeng B (2018) Separability-entanglement classifier via machine learning. Phys Rev A 98(1):012315
Ma Y-C, Yung M-H (2018) Transforming Bell’s inequalities into state classifiers with machine learning. npj Quantum Inf 4(1):34
Mooney GJ, Hill CD, Hollenberg LC (2019) Entanglement in a 20-qubit superconducting quantum computer. Sci Rep 9(1):13465
Morstyn T (2022) Annealing-based quantum computing for combinatorial optimal power flow. IEEE Trans Smart Grid 14(2):1093–1102
Nielsen MA, Chuang IL (2001) Quantum computation and quantum information, vol 2, pp 389–393. Cambridge university press Cambridge
Paini M, Kalev A, Padilha D, Ruck B (2021) Estimating expectation values using approximate quantum states. Quantum 5:413
Pawłowski J, Krawczyk M (2022) Quantification of entanglement with siamese convolutional neural networks. arXiv:2210.07410
Qi X, Hou J (2012) Characterization of optimal entanglement witnesses. Physical Review A 85(2):022334
Qiu P-H, Chen X-G, Shi Y-W (2019) Detecting entanglement with deep quantum neural networks. IEEE Access 7:94310–94320
Qu Y-D, Zhang R-Q, Shen S, Yu J, Li M (2023) Entanglement detection with complex-valued neural networks. Int J Theor Phys 62:1–15
Santurkar S, Tsipras D, Ilyas A, Madry A (2018) How does batch normalization help optimization? Adv Neural Inf Process Syst 31
Srinivas R, Knill E, Sutherland R, Kwiatkowski AT, Knaack HM, Glancy S, Wineland DJ, Burd SC, Leibfried D, Wilson AC, Allcock DT, Slichter D (2021) High-fidelity laser-free universal control of trapped ion qubits. Nature 597:209–213. https://doi.org/10.1038/s41586-021-03809-4
Team QD (2020) Qiskit: an open-source framework for quantum computing. https://doi.org/10.5281/zenodo.2562110https://qiskit.org
Virzí S, Rebufello E, Avella A, Piacentini F, Gramegna M, Berchera IR, Degiovanni IP, Genovese M (2019) Optimal estimation of entanglement and discord in two-qubit states. Sci Rep 9:3030. https://doi.org/10.1038/s41598-019-39334-8
Wang K, Song Z, Zhao X, Wang Z, Wang X (2022) Detecting and quantifying entanglement on near-term quantum devices. npj Quantum Information https://doi.org/10.1038/s41534-022-00556-w
Xie S, Eberly JH (2021) Triangle measure of tripartite entanglement. Phys Rev Lett 127:040403. https://doi.org/10.1103/PhysRevLett.127.040403
Yin J, Li Y, Liao S, Yang M, Cao Y, Zhang L, Ren J-G, Cai W, Liu W, Li S-L, Shu R, Huang Y, Deng L, Li L, Zhang Q, Liu N-L, Chen Y-A, Lu C, Wang X-B, Xu F, Wang J-Y, Peng C-Z, Ekert A, Pan J-W (2020) Entanglement-based secure quantum cryptography over 1,120 kilometres. Nature 582:501–505. https://doi.org/10.1038/s41586-020-2401-y
Yosefpor M, Mostaan MR, Raeisi S (2020) Finding semi-optimal measurements for entanglement detection using autoencoder neural networks. Quantum Sci Technol 5(4). https://doi.org/10.1088/2058-9565/aba34c
Yoshida Y, Okada M (2020) Data-dependence of plateau phenomenon in learning with neural network–statistical mechanical analysis. J Stat Mech Theor 2020. https://doi.org/10.1088/1742-5468/abc62f
Yu C, Qi X, Ma H, He X, Wang C, Zhao Y (2020) LLR: learning learning rates by LSTM for training neural networks. Neurocomputing 394:41–50. https://doi.org/10.1016/j.neucom.2020.01.106
Zangi S, Wu J, Qiao C (2021) Combo separability criteria and lower bound on concurrence. J Phys A Math Theor 55. https://doi.org/10.1088/1751-8121/ac3c80
Author information
Authors and Affiliations
Contributions
AK: conceptualization, methodology, investigation, programming, literature survey, writing. YM: data adjustment, visualization, literature survey, writing. PK: literature survey, revising manuscript. HA: revising manuscript, project administration, supervision. KF: revising manuscript, supervision. MB: revising manuscript, supervision.
Corresponding author
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Supplementary Information
Below is the link to the electronic supplementary material.
Supplementary file 1 (mp4 21310 KB)
Appendices
Appendix A: Two-qubit density matrix
Two-qubit separable mixed states are expressed:
where \(\sum _{i}\lambda _i=1\) and \(0\le \lambda _i\le 1\), summing over \(i=1\) to m. \(\rho _i^A\) and \(\rho _i^B\) are arbitrary density matrices of A and B qubits, respectively. Two-qubit entangled mixed states are expressed as
\(\rho _{i}^{AB}\) is the arbitrary density matrix of the two-qubit entangled state.
Appendix B: Generation of three-qubit density matrix
In the three qubits case, two-qubit entangled states are required to build partial entangled states.
1.1 B.1 Three-qubit separable density matrix
Separable mixed states are expressed:
where \(\sum _{i}\lambda _i=1\) and \(0\le \lambda _i\le 1\), with m iterating from 1 to an arbitrary number. The greater the value of m, the less pure the state.
1.2 B.2 Partial entangled density matrix
Partial entangled mixed states of a three-qubit state are produced in three cases.
Case 1: Partial entangled pairs \(|\psi _{A}\rangle \) and \(|\psi _{B}\rangle \) are generated by
where \(\sum _{i}\lambda _i=1\) and \(0\le \lambda _i\le 1\), with m iterating from 1 to an arbitrary number. \(\rho ^{AB}\) is a density matrix of a two-qubit entangled state.
Case 2: Partial entangled pairs \(|\psi _{B}\rangle \) and \(|\psi _{C}\rangle \) are generated by
where \(\sum _{i}\lambda _i=1\) and \(0\le \lambda _i\le 1\), \(\rho _i^{BC}\) is an arbitrary density matrix of a two-qubit entangled state.
Case 3: Partial entangled pairs \(|\psi _{A}\rangle \) and \(|\psi _{C}\rangle \) are generated by state vectors of the entangled state \(|\psi _{AC}\rangle \) and separated state \(|\psi _B\rangle \) considered as
and
Therefore, the partial entangled states are considered as
where a and b are corespondent amplitudes of states (B6) and (B7). Ultimately, the partial entangled states are generated by
where \(\sum _{i}\lambda _i=1\) and \(0\le \lambda _i\le 1\) and \(|\psi _{B|AC}\rangle \) is the generated partial entangled state.
1.3 B.3 Three-qubit GHZ state
The state vector of a random three-qubit state that GHZ is applied to is described as
with initial states:
where
The angles belong to the intervals \(\delta \in (0,\ \pi /4]\), \((\alpha ,\ \beta ,\ \gamma )\in (0,\ \pi /2]\), and \(\phi \in [0,\ 2\pi )\).
1.4 B.4 Three-qubit W-state
A random state vector that undergoes the W-state operation can be written as
where
is the normalization factor and \(|\phi \rangle \) is a superposition of remaining states with W-state.
1.5 B.5 Three-qubit graph state
The graph state can be considered as
where normalization factor is
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Kookani, A., Mafi, Y., Kazemikhah, P. et al. XpookyNet: advancement in quantum system analysis through convolutional neural networks for detection of entanglement. Quantum Mach. Intell. 6, 50 (2024). https://doi.org/10.1007/s42484-024-00183-y
Received:
Accepted:
Published:
DOI: https://doi.org/10.1007/s42484-024-00183-y