Quantum and quantum-like machine learning: a note on differences and similarities

Abstract

In the past few decades, researchers have extensively investigated the applications of quantum computation and quantum information to machine learning with remarkable results. This, in turn, has led to the emergence of quantum machine learning as a separate discipline, whose main goal is to transform standard machine learning algorithms into quantum algorithms which can be implemented on quantum computers. One further research programme has involved using quantum information to create new quantum-like algorithms for classical computers (Sergioli et al. in Int J Theor Phys 56(12):3880–3888, 2017; PLoS ONE 14:e0216224, 2019. https://doi.org/10.1371/journal.pone.0216224; Int J Quantum Inf 16(8):1840011, 2018a; Soft Comput 22(3):691–705, 2018b). This brief survey summarises and compares both approaches and also outlines the main motivations behind them.

This is a preview of subscription content, access via your institution.

Fig. 1
Fig. 2

Notes

  1. 1.

    It should be stressed that quantum-like algorithms implemented by the NQiML approach are not a mere translation of classical algorithms. For instance, in Sergioli et al. (2018b, Section 2.1), the author introduces a quantum-like version of the NMC, which is very different from a mere quantum-theoretic translation of the NMC.

  2. 2.

    For instance, a very usual pre-processing consists in the normalisation of all the vectors of the dataset.

References

  1. Aaronson S (2007) The learnability of quantum states. Proc R Soc Lond A Math Phys Eng Sci 463:3089–3114

    MathSciNet  MATH  Google Scholar 

  2. Aïmeur E, Brassard G, Gambs S (2006) Machine learning in a quantum world. In: Conference of the Canadian Society for Computational Studies of Intelligence. Springer, Berlin

  3. Audenaert KMR, Calsamiglia J, Munoz-Tapia R, Bagan E, Masanes LI, Acin A, Verstraete F (2017) Discriminating states: the quantum Chernof bound. Phys Rev Lett 98:160501

    Google Scholar 

  4. Bergou J, Herzog U, Hillery M (2004) Discrimination of quantum states. In: Lectures notes in Physics, vol 649. Springer, Berlin, pp 417–465

  5. Bisio A, Chiribella G, Mauro G, Ariano D, Facchini S, Perinotti P (2010) Optimal quantum learning of unitary transformation. Phys Rev A 82(3):032324

    MathSciNet  Google Scholar 

  6. Carrasquilla J, Melko RG (2017) Machine learning phases of matter. Nat Phys 13:431–434

    Google Scholar 

  7. Castelvecchi D (2017) IBM’s quantum cloud computer goes commercial. Nature 543(7664):159

    Google Scholar 

  8. Chefles A (2000) Quantum state discriminator. Contemp Phys 41(6):401–424

    Google Scholar 

  9. Dalla Chiara ML, Giuntini R, Leporini R, Negri E, Sergioli G (2015) Quantum information, cognition and music. Front Psychol 6:1583

    Google Scholar 

  10. Deutsch D (1985) Quantum theory, the Church–Turing principle and the universal quantum computer. Proc R Soc Lond A 400:97–117

    MathSciNet  MATH  Google Scholar 

  11. Duda RO, Hart PE, Stork DG (2000) Pattern classification, 2nd edn. Wiley Interscience, New York

    MATH  Google Scholar 

  12. Feynamn R (1982) Simulating physics with computers. Int J Theor Phys 21(6/7):467–488

    MathSciNet  Google Scholar 

  13. Freytes H, Sergioli G (2014) Fuzzy approach for Toffoli gate in quantum computation with mixed states. Rep Math Phys 74(2):159–180

    MathSciNet  MATH  Google Scholar 

  14. Gambs S (2008) Quantum classification. arXiv:0809.0444v2

  15. Guta M, Kotlowski W (2010) Quantum learning: asymptotically optimal classification of qubit states. New J Phys 12:123032

    MathSciNet  Google Scholar 

  16. Hayashi A, Horibe M, Hashimoto T (2005) Quantum pure-state identification. Phys Rev A 72(5):052306

    Google Scholar 

  17. Helstrom CW (1976) Quantum detection and estimation theory. Academic Press, New York

    MATH  Google Scholar 

  18. Hilbert M, Lopez P (2011) The World’s technological capacity to store, communicate, and compute information. Science 332:60

    Google Scholar 

  19. Holik F, Sergioli G, Freytes H, Plastino A (2017) Pattern recognition in non-Kolmogorovian structures. Found Sci 23(1):119–132

    MATH  Google Scholar 

  20. Lloyd S, Mohseni M, Rebentrost P (2013) Quantum algorithms for supervised and unsupervised machine learning. arXiv:1307.0411

  21. Lloyd S, Mohseni M, Rebentrost P (2014) Quantum principal component analysis. Nat Phys 10(9):631–633

    Google Scholar 

  22. Lu S, Braunstein SL (2014) Quantum decision tree classifier. Quantum Inf Process 13(3):757–770

    MathSciNet  MATH  Google Scholar 

  23. Manju A, Nigam MJ (2014) Applications of quantum inspired computational intelligence: a survey. Artif Intell Rev 42(1):79–156

    Google Scholar 

  24. Melkikh AV, Khrennikov A, Yampolskiy RV (2019) Quantum metalanguage and new cognitive synthesis. NeuroQuantology 17:72–96

    Google Scholar 

  25. Nielsen MA, Chuang IL (2010) Quantum computation and quantum information, 10th Anniversary edn. Cambridge University Press, Cambridge

  26. Qiu D (2007) Minimum-error discrimination between mixed states. arXiv:0707.3970 [quant-phis]

  27. Santucci E (2017) Quantum minimum distance classifier. Entropy 19(12):659

    MathSciNet  Google Scholar 

  28. Santucci E, Sergioli G (2018) Classification problem in a quantum framework. In: Khrennikov A, Bourama T (eds) Quantum foundations, probability and information, proceedings of the quantum and beyond conference, Vaxjo, Sweden, 13–16 June 2016. Springer, Berlin, Germany, in press

  29. Sasaki M, Carlini A (2002) Quantum learning and universal quantum matching machine. Phys Rev A 66(2):022303

    MathSciNet  Google Scholar 

  30. Schuld M, Petruccione F (2018) Supervised learning with quantum computers. In: Quantum science and technology. Springer, Berlin

  31. Schuld M, Sinayskiy I, Petruccione F (2014a) An introduction to quantum machine learning. Contemp Phys 56(2):172–185

    MATH  Google Scholar 

  32. Schuld M, Sinayskiy I, Petruccione F (2014b) The quest for a quantum neural network. Quantum Inf Process 13(11):2567–2586

    MathSciNet  MATH  Google Scholar 

  33. Schuld M, Fingerhuth M, Petruccione F (2017) Implementing distance-based classifier with a quantum interference circuit. Europhys Lett 119(6):60002

    Google Scholar 

  34. Sergioli G, Santucci E, Didaci L, Miszczak J, Giuntini R (2016) A quantum-inspired version of the nearest mean classifier. Soft Comput 22(3):691–705

    MATH  Google Scholar 

  35. Sergioli G, Bosyk GM, Santucci E, Giuntini R (2017) A quantum-inspired version of the classification problem. Int J Theor Phys 56(12):3880–3888

    MathSciNet  MATH  Google Scholar 

  36. Sergioli G, Santucci E, Didaci L, Miszczak JA, Giuntini R (2018a) A quantum inspired version of the NMC classifier. Soft Comput 22(3):691–705

    MATH  Google Scholar 

  37. Sergioli G, Russo G, Santucci E, Stefano A, Torrisi SE, Palmucci S, Vancheri C, Giuntini R (2018b) Quantum-inspired minimum distance classification in biomedical context. Int J Quantum Inf 16(8):1840011

    MATH  Google Scholar 

  38. Sergioli G, Giuntini R, Freytes H (2019) A new quantum approach to binary classification. PLoS ONE 14:e0216224. https://doi.org/10.1371/journal.pone.0216224

    Google Scholar 

  39. Trugenberg CA (2002) Quantum pattern recognition. Quantum Inf Process 1(6):471–493

    MathSciNet  Google Scholar 

  40. Wiebe N, Kapoor A, Svore KM (2015) Quantum nearest-neighbor algorithms for machine learning. Quantum Inf Comput 15(34):318–358

    Google Scholar 

  41. Wittek P (2014) Quantum machine learning: what quantum computing means to data mining. Academic Press, New York

    MATH  Google Scholar 

Download references

Acknowledgements

I warmly thank Claudio Ternullo for the careful linguistic revision of the last version of the manuscript.

Funding

This work has been partially supported by the Project “Strategies and Technologies for Scientific Education and Dissemination” (CUP No. F71I17000330002) founded by Fondazione di Sardegna.

Author information

Affiliations

Authors

Corresponding author

Correspondence to Giuseppe Sergioli.

Ethics declarations

Conflict of interest

The author does not have any conflicts of interest.

Ethical standard

This article does not contain any studies with human participants performed by any of the authors.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Communicated by F. Holik.

Rights and permissions

Reprints and Permissions

About this article

Verify currency and authenticity via CrossMark

Cite this article

Sergioli, G. Quantum and quantum-like machine learning: a note on differences and similarities. Soft Comput 24, 10247–10255 (2020). https://doi.org/10.1007/s00500-019-04429-x

Download citation

Keywords

  • Quantum machine learning
  • Quantum information
  • Binary classification