Skip to main content
SpringerLink
Log in

A duplication-free quantum neural network for universal approximation

  • Article
  • Editor’s Focus
  • Published:
Science China Physics, Mechanics & Astronomy Aims and scope Submit manuscript

Abstract

Different from the concept of universal computation, the universality of a quantum neural network focuses on the ability to approximate arbitrary functions and is an important guarantee for effectiveness. However, conventional approaches of constructing a universal quantum neural network may result in a huge quantum register that is challenging to implement due to noise on a near-term device. To address this, we propose a simple design of a duplication-free quantum neural network whose universality can be rigorously proven. Specifically, instead of using multiple duplicates of the quantum register, our method relies on a single quantum register combined with multiple activation functions to create nonlinearity and achieve universality. Accordingly, our proposal requires significantly fewer qubits with shallower circuits, and hence substantially reduces the resource overhead and the noise effect. In addition, simulations demonstrate that our universality design is able to achieve a better learning accuracy in the presence of noise, illustrating a great potential in solving larger-scale learning problems on near-term devices.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

References

  1. H. Zheng, J. Fu, T. Mei, and J. Luo, in Learning multi-attention convolutional neural network for fine-grained image recognition: Proceedings of the IEEE International Conference on Computer Vision (ICCV), Venice, 2017.

  2. B. Shi, X. Bai, and C. Yao, IEEE Trans. Pattern Anal. Mach. Intell. 39, 2298 (2017).

    Article  Google Scholar 

  3. S. Albawi, T. A. Mohammed, and S. Al-Zawi, in Understanding of a convolutional neural network: Proceedings of the 2017 International Conference on Engineering and Technology (ICET), Antalya, Akdeniz University, 2017.

    Book  Google Scholar 

  4. W. Li, and D.-L. Deng, Sci. China-Phys. Mech. Astron. 65, 220301 (2022), arXiv: 2108.13421.

    Article  ADS  Google Scholar 

  5. Y. Goldberg, Jair 57, 345 (2016).

    Article  Google Scholar 

  6. Y. Goldberg, Synth. Lectures Hum. Lang. Tech. 10, 1 (2017).

    Article  Google Scholar 

  7. R. Collobert, and J. Weston, in A unified architecture for natural language processing: deep Neural Networks with Multitask Learning: Proceedings of the 25th International Conference on Machine Learning, Helsinki, 2008.

  8. B. T. Nugraha, S. F. Su, and Fahmizal, in Towards self-driving car using convolutional neural network and road lane detector: Proceedings of the International Conference on Automation, Cognitive Science, Optics, Micro Electro-Mechanical System, and Information Technology, Jakarta, 2017.

  9. T. D. Do, M. T. Duong, Q. V. Dang, and M. H. Le, in Real-time self-driving car navigation using deep neural network: Proceedings of the International Conference on Green Technology and Sustainable Development, Ho Chi Minh City, 2018.

  10. M. Bojarski, P. Yeres, A. Choromanska, K. Choromanski, B. Firner, L. Jackel, and U. Muller, arXiv: 1704.07911.

  11. J. Biamonte, P. Wittek, N. Pancotti, P. Rebentrost, N. Wiebe, and S. Lloyd, Nature 549, 195 (2017), arXiv: 1611.09347.

    Article  ADS  Google Scholar 

  12. G. Carleo, and M. Troyer, Science 355, 602 (2017), arXiv: 1606.02318.

    Article  ADS  MathSciNet  Google Scholar 

  13. D. L. Deng, X. Li, and S. Das Sarma, Phys. Rev. X 7, 021021 (2017), arXiv: 1701.04844.

    Google Scholar 

  14. J. A. Garrido Torres, V. Gharakhanyan, N. Artrith, T. H. Eegholm, and A. Urban, Nat. Commun. 12, 7012 (2021).

    Article  ADS  Google Scholar 

  15. K. T. Schutt, M. Gastegger, A. Tkatchenko, K. R. Müller, and R. J. Maurer, Nat. Commun. 10, 5024 (2019).

    Article  ADS  Google Scholar 

  16. X. Gao, and L. M. Duan, Nat. Commun. 8, 662 (2017).

    Article  ADS  Google Scholar 

  17. F. M. Paruzzo, A. Hofstetter, F. Musil, S. De, M. Ceriotti, and L. Emsley, Nat. Commun. 9, 4501 (2018), arXiv: 1805.11541.

    Article  ADS  Google Scholar 

  18. H. Y. Huang, M. Broughton, J. Cotler, S. Chen, J. Li, M. Mohseni, H. Neven, R. Babbush, R. Kueng, J. Preskill, and J. R. McClean, Science 376, 1182 (2022), arXiv: 2112.00778.

    Article  ADS  MathSciNet  Google Scholar 

  19. N. Wiebe, D. Braun, and S. Lloyd, Phys. Rev. Lett. 109, 050505 (2012), arXiv: 1204.5242.

    Article  ADS  Google Scholar 

  20. P. Rebentrost, M. Mohseni, and S. Lloyd, Phys. Rev. Lett. 113, 130503 (2014), arXiv: 1307.0471.

    Article  ADS  Google Scholar 

  21. N. Wiebe, A. Kapoor, and K. M. Svore, Quantum Info. Comput. 15, 316 (2015).

    Google Scholar 

  22. S. Lloyd, M. Mohseni, and P. Rebentrost, Nat. Phys. 10, 631 (2014), arXiv: 1307.0401.

    Article  Google Scholar 

  23. M. Schuld, I. Sinayskiy, and F. Petruccione, Phys. Rev. A 94, 022342 (2016), arXiv: 1601.07823.

    Article  ADS  Google Scholar 

  24. G. D. Paparo, and M. Martin-Delgado, Sci. Rep. 2, 444 (2012).

    Article  ADS  Google Scholar 

  25. D. Y. Dong, C. L. Chen, H. X. Li, and T.-J. Tarn, IEEE Trans. Syst. Man. Cybern. B 38, 1207 (2008).

    Article  Google Scholar 

  26. V. Saggio, B. E. Asenbeck, A. Hamann, T. Strömberg, P. Schiansky, V. Dunjko, N. Friis, N. C. Harris, M. Hochberg, D. Englund, S. Wölk, H. J. Briegel, and P. Walther, Nature 591, 229 (2021), arXiv: 2103.06294.

    Article  ADS  Google Scholar 

  27. G. D. Paparo, V. Dunjko, A. Makmal, M. A. Martin-Delgado, and H. J. Briegel, Phys. Rev. X 4, 031002 (2014).

    Google Scholar 

  28. N. Liu, and P. Rebentrost, Phys. Rev. A 97, 042315 (2018), arXiv: 1710.07405.

    Article  ADS  Google Scholar 

  29. M. H. Amin, E. Andriyash, J. Rolfe, B. Kulchytskyy, and R. Melko, Phys. Rev. X 8, 021050 (2018).

    Google Scholar 

  30. S. Aaronson, Nat. Phys. 11, 291 (2015).

    Article  Google Scholar 

  31. H. Y. Huang, M. Broughton, M. Mohseni, R. Babbush, S. Boixo, H. Neven, and J. R. McClean, Nat. Commun. 12, 2631 (2021).

    Article  ADS  Google Scholar 

  32. K. Mitarai, M. Negoro, M. Kitagawa, and K. Fujii, Phys. Rev. A 98, 032309 (2018).

    Article  ADS  Google Scholar 

  33. M. Schuld, A. Bocharov, K. M. Svore, and N. Wiebe, Phys. Rev. A 101, 032308 (2020).

    Article  ADS  MathSciNet  Google Scholar 

  34. I. Cong, S. Choi, and M. D. Lukin, Nat. Phys. 15, 1273 (2019), arXiv: 1810.03787.

    Article  Google Scholar 

  35. H. L. Huang, X. Y. Xu, C. Guo, G. Tian, S. J. Wei, X. Sun, W. S. Bao, and G. L. Long, Sci. China-Phys. Mech. Astron. 66, 250302 (2023).

    Article  ADS  Google Scholar 

  36. J. Liu, K. H. Lim, K. L. Wood, W. Huang, C. Guo, and H.-L. Huang, Sci. China-Phys. Mech. Astron. 64, 290311 (2021).

    Article  ADS  Google Scholar 

  37. J. R. McClean, S. Boixo, V. N. Smelyanskiy, R. Babbush, and H. Neven, Nat. Commun. 9, 4812 (2018), arXiv: 1803.11173.

    Article  ADS  Google Scholar 

  38. P. Rebentrost, T. R. Bromley, C. Weedbrook, and S. Lloyd. Phys. Rev. A 98, 042308 (2018).

    Article  ADS  Google Scholar 

  39. Z. Holmes, K. Sharma, M. Cerezo, and P. J. Coles, PRX Quantum 3, 010313 (2022), arXiv: 2101.02138.

    Article  ADS  Google Scholar 

  40. S. Wang, E. Fontana, M. Cerezo, K. Sharma, A. Sone, L. Cincio, and P. J. Coles, Nat. Commun. 12, 6961 (2021), arXiv: 2007.14384.

    Article  ADS  Google Scholar 

  41. S. Thanasilp, S. Wang, N. A. Nghiem, P. J. Coles, and M. Cerezo, arXiv: 2110.14753.

  42. S. Wei, Y. Chen, Z. Zhou, and G. Long, AAPPS Bull. 32, 1 (2022).

    Article  ADS  Google Scholar 

  43. D.-L. Deng, Sci. China-Phys. Mech. Astron. 64, 100331 (2021).

    Article  ADS  Google Scholar 

  44. M. Cerezo, A. Sone, T. Volkoff, L. Cincio, and P. J. Coles, Nat. Commun. 12, 1791 (2021), arXiv: 2001.00550.

    Article  ADS  Google Scholar 

  45. Z. Cai. Quantum 5, 548 (2021).

    Article  Google Scholar 

  46. S. Endo, S. C. Benjamin, and Y. Li, Phys. Rev. X 8, 031027 (2018).

    Google Scholar 

  47. Z. Cai, R. Babbush, S. C. Benjamin, S. Endo, W. J. Huggins, Y. Li, J. R. McClean, and T. E. O’Brien, arXiv: 2210.00921.

  48. K. Hornik, M. Stinchcombe, and H. White, Neural Networks 2, 359 (1989).

    Article  Google Scholar 

  49. M. Leshno, V. Y. Lin, A. Pinkus, and S. Schocken. Neural Networks 6, 861 (1993).

    Article  Google Scholar 

  50. A. Pérez-Salinas, A. Cervera-Lierta, E. Gil-Fuster, and J. I. Latorre, Quantum 4, 226 (2020), arXiv: 1907.02085.

    Article  Google Scholar 

  51. M. Schuld, R. Sweke, and J. J. Meyer. Phys. Rev. A 103, 032430 (2021).

    Article  ADS  Google Scholar 

  52. Y. D. Cao, G. G. Guerreschi, and A. Aspuru-Guzik, arXiv: 1711.11240.

  53. S. Yan, H. Qi, and W. Cui, Phys. Rev. A 102, 052421 (2020), arXiv: 2011.03429.

    Article  ADS  MathSciNet  Google Scholar 

  54. F. Tacchino, C. Macchiavello, D. Gerace, and D. Bajoni, npj Quantum Inf. 5, 26 (2019), arXiv: 1811.02266.

    Article  ADS  Google Scholar 

  55. L. B. Kristensen, M. Degroote, P. Wittek, A. Aspuru-Guzik, and N. T. Zinner, npj Quantum Inf. 7, 59 (2021).

    Article  ADS  Google Scholar 

  56. E. Torrontegui, and J. J. García-Ripoll, EPL 125, 30004 (2019), arXiv: 1801.00934.

    Article  ADS  Google Scholar 

  57. K. Beer, D. Bondarenko, T. Farrelly, T. J. Osborne, R. Salzmann, D. Scheiermann, and R. Wolf, Nat. Commun. 11, 808 (2020), arXiv: 1902.10445.

    Article  ADS  Google Scholar 

  58. M. Schuld, I. Sinayskiy, and F. Petruccione, Phys. Lett. A 379, 660 (2015).

    Article  Google Scholar 

  59. K. H. Wan, O. Dahlsten, H. Kristjaínsson, R. Gardner, and M. S. Kim, npj Quantum Inf. 3, 36 (2017), arXiv: 1612.01045.

    Article  ADS  Google Scholar 

  60. C. Runge, Zeitschrift für Mathematik und Physik 46, 224 (1901).

    Google Scholar 

  61. S. C. Brenner, and L. R. Scott, The Mathematical Theory of Finite Element Methods (Springer, New York, 2007).

    Google Scholar 

  62. I. Goodfellow, Y. Bengio, and A. Courville, Deep Learning (MIT Press, Cambridge, 2016).

    MATH  Google Scholar 

  63. M. Plesch, and C. Brukner, Phys. Rev. A 83, 032302 (2011), arXiv: 1003.5760.

    Article  ADS  Google Scholar 

  64. K. Nakaji, S. Uno, Y. Suzuki, R. Raymond, T. Onodera, T. Tanaka, H. Tezuka, N. Mitsuda, and N. Yamamoto, Phys. Rev. Res. 4, 023136 (2022).

    Article  Google Scholar 

  65. M. Schuld, arXiv: 2101.11020.

  66. P. Gao, K. Li, S. Wei, and G.-L. Long, Sci. China-Phys. Mech. Astron. 64, 100311 (2021).

    Article  ADS  Google Scholar 

  67. L. Bottou, in Large-scale machine learning with stochastic gradient descent: Proceedings of the 19th International Conference on Computational Statistics (Springer, Paris, 2010), p. 177.

    MATH  Google Scholar 

  68. D. Kingma, and J. Ba, in Adam: A Method for Stochastic Optimization: Proceedings of the International Conference on Learning Representations, San Diego, 2015.

  69. A. Buckley, and A. Lenir, ACM Trans. Math. Softw. 11, 103 (1985).

    Article  Google Scholar 

  70. C. M. Bishop, Pattern Recognition and Machine Learning (Springer, Berlin, 2006).

    MATH  Google Scholar 

  71. Y. LeCun, C. Cortes, and C. Burges, Mnist Handwritten Digit Database (2010).

  72. D. Dua, and C. Graff, UCI Mach Learn Repository (2017).

  73. F. D. M. Haldane, Phys. Rev. Lett. 50, 1153 (1983).

    Article  ADS  MathSciNet  Google Scholar 

  74. H. Hahn, J. fur die Reine und Angew. Math. 1927, 214 (1927).

    Article  Google Scholar 

  75. M. Frechet, CR Acad. Sci. Paris 144, 1414 (1907).

    Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Institute of Fundamental and Frontier Sciences, University of Electronic Science and Technology of China, Chengdu, 610051, China

    Xiaokai Hou, Guanyu Zhou, Qingyu Li, Shan Jin & Xiaoting Wang

Authors
  1. Xiaokai Hou
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Guanyu Zhou
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Qingyu Li
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Shan Jin
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Xiaoting Wang
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding authors

Correspondence to Guanyu Zhou or Xiaoting Wang.

Additional information

This work was supported by the National Key R&D Program of China (Grant No. 2018YFA0306703), and the National Natural Science Foundation of China (Grant No. 92265208). We also thank Chu Guo, Bujiao Wu, Yusen Wu, Shaojun Wu, Yuhan Huang, Donghong Han, Yingli Yang and Yi Tian for helpful discussions.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Hou, X., Zhou, G., Li, Q. et al. A duplication-free quantum neural network for universal approximation. Sci. China Phys. Mech. Astron. 66, 270362 (2023). https://doi.org/10.1007/s11433-023-2098-8

Download citation

  • Received:

  • Accepted:

  • Published:

  • DOI: https://doi.org/10.1007/s11433-023-2098-8

Search

Navigation