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.
References
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.
B. Shi, X. Bai, and C. Yao, IEEE Trans. Pattern Anal. Mach. Intell. 39, 2298 (2017).
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.
W. Li, and D.-L. Deng, Sci. China-Phys. Mech. Astron. 65, 220301 (2022), arXiv: 2108.13421.
Y. Goldberg, Jair 57, 345 (2016).
Y. Goldberg, Synth. Lectures Hum. Lang. Tech. 10, 1 (2017).
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.
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.
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.
M. Bojarski, P. Yeres, A. Choromanska, K. Choromanski, B. Firner, L. Jackel, and U. Muller, arXiv: 1704.07911.
J. Biamonte, P. Wittek, N. Pancotti, P. Rebentrost, N. Wiebe, and S. Lloyd, Nature 549, 195 (2017), arXiv: 1611.09347.
G. Carleo, and M. Troyer, Science 355, 602 (2017), arXiv: 1606.02318.
D. L. Deng, X. Li, and S. Das Sarma, Phys. Rev. X 7, 021021 (2017), arXiv: 1701.04844.
J. A. Garrido Torres, V. Gharakhanyan, N. Artrith, T. H. Eegholm, and A. Urban, Nat. Commun. 12, 7012 (2021).
K. T. Schutt, M. Gastegger, A. Tkatchenko, K. R. Müller, and R. J. Maurer, Nat. Commun. 10, 5024 (2019).
X. Gao, and L. M. Duan, Nat. Commun. 8, 662 (2017).
F. M. Paruzzo, A. Hofstetter, F. Musil, S. De, M. Ceriotti, and L. Emsley, Nat. Commun. 9, 4501 (2018), arXiv: 1805.11541.
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.
N. Wiebe, D. Braun, and S. Lloyd, Phys. Rev. Lett. 109, 050505 (2012), arXiv: 1204.5242.
P. Rebentrost, M. Mohseni, and S. Lloyd, Phys. Rev. Lett. 113, 130503 (2014), arXiv: 1307.0471.
N. Wiebe, A. Kapoor, and K. M. Svore, Quantum Info. Comput. 15, 316 (2015).
S. Lloyd, M. Mohseni, and P. Rebentrost, Nat. Phys. 10, 631 (2014), arXiv: 1307.0401.
M. Schuld, I. Sinayskiy, and F. Petruccione, Phys. Rev. A 94, 022342 (2016), arXiv: 1601.07823.
G. D. Paparo, and M. Martin-Delgado, Sci. Rep. 2, 444 (2012).
D. Y. Dong, C. L. Chen, H. X. Li, and T.-J. Tarn, IEEE Trans. Syst. Man. Cybern. B 38, 1207 (2008).
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.
G. D. Paparo, V. Dunjko, A. Makmal, M. A. Martin-Delgado, and H. J. Briegel, Phys. Rev. X 4, 031002 (2014).
N. Liu, and P. Rebentrost, Phys. Rev. A 97, 042315 (2018), arXiv: 1710.07405.
M. H. Amin, E. Andriyash, J. Rolfe, B. Kulchytskyy, and R. Melko, Phys. Rev. X 8, 021050 (2018).
S. Aaronson, Nat. Phys. 11, 291 (2015).
H. Y. Huang, M. Broughton, M. Mohseni, R. Babbush, S. Boixo, H. Neven, and J. R. McClean, Nat. Commun. 12, 2631 (2021).
K. Mitarai, M. Negoro, M. Kitagawa, and K. Fujii, Phys. Rev. A 98, 032309 (2018).
M. Schuld, A. Bocharov, K. M. Svore, and N. Wiebe, Phys. Rev. A 101, 032308 (2020).
I. Cong, S. Choi, and M. D. Lukin, Nat. Phys. 15, 1273 (2019), arXiv: 1810.03787.
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).
J. Liu, K. H. Lim, K. L. Wood, W. Huang, C. Guo, and H.-L. Huang, Sci. China-Phys. Mech. Astron. 64, 290311 (2021).
J. R. McClean, S. Boixo, V. N. Smelyanskiy, R. Babbush, and H. Neven, Nat. Commun. 9, 4812 (2018), arXiv: 1803.11173.
P. Rebentrost, T. R. Bromley, C. Weedbrook, and S. Lloyd. Phys. Rev. A 98, 042308 (2018).
Z. Holmes, K. Sharma, M. Cerezo, and P. J. Coles, PRX Quantum 3, 010313 (2022), arXiv: 2101.02138.
S. Wang, E. Fontana, M. Cerezo, K. Sharma, A. Sone, L. Cincio, and P. J. Coles, Nat. Commun. 12, 6961 (2021), arXiv: 2007.14384.
S. Thanasilp, S. Wang, N. A. Nghiem, P. J. Coles, and M. Cerezo, arXiv: 2110.14753.
S. Wei, Y. Chen, Z. Zhou, and G. Long, AAPPS Bull. 32, 1 (2022).
D.-L. Deng, Sci. China-Phys. Mech. Astron. 64, 100331 (2021).
M. Cerezo, A. Sone, T. Volkoff, L. Cincio, and P. J. Coles, Nat. Commun. 12, 1791 (2021), arXiv: 2001.00550.
Z. Cai. Quantum 5, 548 (2021).
S. Endo, S. C. Benjamin, and Y. Li, Phys. Rev. X 8, 031027 (2018).
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.
K. Hornik, M. Stinchcombe, and H. White, Neural Networks 2, 359 (1989).
M. Leshno, V. Y. Lin, A. Pinkus, and S. Schocken. Neural Networks 6, 861 (1993).
A. Pérez-Salinas, A. Cervera-Lierta, E. Gil-Fuster, and J. I. Latorre, Quantum 4, 226 (2020), arXiv: 1907.02085.
M. Schuld, R. Sweke, and J. J. Meyer. Phys. Rev. A 103, 032430 (2021).
Y. D. Cao, G. G. Guerreschi, and A. Aspuru-Guzik, arXiv: 1711.11240.
S. Yan, H. Qi, and W. Cui, Phys. Rev. A 102, 052421 (2020), arXiv: 2011.03429.
F. Tacchino, C. Macchiavello, D. Gerace, and D. Bajoni, npj Quantum Inf. 5, 26 (2019), arXiv: 1811.02266.
L. B. Kristensen, M. Degroote, P. Wittek, A. Aspuru-Guzik, and N. T. Zinner, npj Quantum Inf. 7, 59 (2021).
E. Torrontegui, and J. J. García-Ripoll, EPL 125, 30004 (2019), arXiv: 1801.00934.
K. Beer, D. Bondarenko, T. Farrelly, T. J. Osborne, R. Salzmann, D. Scheiermann, and R. Wolf, Nat. Commun. 11, 808 (2020), arXiv: 1902.10445.
M. Schuld, I. Sinayskiy, and F. Petruccione, Phys. Lett. A 379, 660 (2015).
K. H. Wan, O. Dahlsten, H. Kristjaínsson, R. Gardner, and M. S. Kim, npj Quantum Inf. 3, 36 (2017), arXiv: 1612.01045.
C. Runge, Zeitschrift für Mathematik und Physik 46, 224 (1901).
S. C. Brenner, and L. R. Scott, The Mathematical Theory of Finite Element Methods (Springer, New York, 2007).
I. Goodfellow, Y. Bengio, and A. Courville, Deep Learning (MIT Press, Cambridge, 2016).
M. Plesch, and C. Brukner, Phys. Rev. A 83, 032302 (2011), arXiv: 1003.5760.
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).
M. Schuld, arXiv: 2101.11020.
P. Gao, K. Li, S. Wei, and G.-L. Long, Sci. China-Phys. Mech. Astron. 64, 100311 (2021).
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.
D. Kingma, and J. Ba, in Adam: A Method for Stochastic Optimization: Proceedings of the International Conference on Learning Representations, San Diego, 2015.
A. Buckley, and A. Lenir, ACM Trans. Math. Softw. 11, 103 (1985).
C. M. Bishop, Pattern Recognition and Machine Learning (Springer, Berlin, 2006).
Y. LeCun, C. Cortes, and C. Burges, Mnist Handwritten Digit Database (2010).
D. Dua, and C. Graff, UCI Mach Learn Repository (2017).
F. D. M. Haldane, Phys. Rev. Lett. 50, 1153 (1983).
H. Hahn, J. fur die Reine und Angew. Math. 1927, 214 (1927).
M. Frechet, CR Acad. Sci. Paris 144, 1414 (1907).
Author information
Authors and Affiliations
Corresponding authors
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
About this article
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
Received:
Accepted:
Published:
DOI: https://doi.org/10.1007/s11433-023-2098-8