No Access

Quantum enhanced cross-validation for near-optimal neural networks architecture selection

Departamento de Computação, Universidade Federal Rural de Pernambuco, Rua Dom Manoel de Medeiros, s/n. Campus Dois Irmãos, 52171-900, Recife, Pernambuco, Brazil

E-mail Address: priscila.marques@ufrpe.br

Search for more papers by this author

Rodrigo S. Sousa

Departamento de Computação, Universidade Federal Rural de Pernambuco, Rua Dom Manoel de Medeiros, s/n. Campus Dois Irmãos, 52171-900, Recife, Pernambuco, Brazil

E-mail Address: rodrigo.silvasouza@ufrpe.br

Search for more papers by this author

Ismael C. S. Araujo

Departamento de Computação, Universidade Federal Rural de Pernambuco, Rua Dom Manoel de Medeiros, s/n. Campus Dois Irmãos, 52171-900, Recife, Pernambuco, Brazil

E-mail Address: ismael.cesar@ufrpe.br

Search for more papers by this author

, and

Adenilton J. da Silva

Departamento de Computação, Universidade Federal Rural de Pernambuco, Rua Dom Manoel de Medeiros, s/n. Campus Dois Irmãos, 52171-900, Recife, Pernambuco, Brazil

E-mail Address: adenilton.silva@ufrpe.br

Corresponding author.

Search for more papers by this author

https://doi.org/10.1142/S0219749918400051Cited by:4 (Source: Crossref)

This article is part of the issue:

Special Issue on Quantum Techniques in Machine Learning; Guest Editors: Alessandra Di Pierro and Stefano Mancini

Abstract

This paper proposes a quantum-classical algorithm to evaluate and select classical artificial neural networks architectures. The proposed algorithm is based on a probabilistic quantum memory (PQM) and the possibility to train artificial neural networks (ANN) in superposition. We obtain an exponential quantum speedup in the evaluation of neural networks. We also verify experimentally through a reduced experimental analysis that the proposed algorithm can be used to select near-optimal neural networks.

Keywords:

References

1. W. S. McCulloch and W. Pitts, Bull. Math. Biophys. 5 (4) (1943) 115. Crossref, Google Scholar
2. D. O. Hebb, The Organization of Behavior: A Neuropsychological Theory (Psychology Press, 2005). Crossref, Google Scholar
3. D. E. Rumelhart, G. E. Hinton and R. J. Williams, Nature 323 (9) (1986) 533. Crossref, Web of Science, Google Scholar
4. S. Samarasinghe, Neural Networks for Applied Sciences and Engineering: From Fundamentals to Complex Pattern Recognition (CRC Press, 2016). Crossref, Google Scholar
5. J. Xu, B. Xu, P. Wang, S. Zheng, G. Tian and J. Zhao, Neural Netw. 88 (2017) 22. Crossref, Web of Science, Google Scholar
6. L. A. Gatys, A. S. Ecker and M. Bethge, Image style transfer using convolutional neural networks, in Proc. IEEE Conf. Computer Vision and Pattern Recognition (IEEE, 2016), pp. 2414–2423. Google Scholar
7. W. Chan, N. Jaitly, Q. Le and O. Vinyals, Listen, attend and spell: A neural network for large vocabulary conversational speech recognition, 2016 IEEE Int. Conf. Acoustics, Speech and Signal Processing (ICASSP), (IEEE, 2016), pp. 4960–4964. Google Scholar
8. V. K. Ojha, A. Abraham and V. Snášel, Eng. Appl. Arti. Intell. 60 (2017) 97. Crossref, Web of Science, Google Scholar
9. A. Abraham, Neurocomput. 56 (2004) 1. Crossref, Web of Science, Google Scholar
10. J. Ilonen, J. Kamarainen and J. Lampinen, Neural Process. Lett. 17 (1) (2003) 93. Crossref, Web of Science, Google Scholar
11. D. J. Montana and L. Davis, Training feedforward neural networks using genetic algorithms, in Proc. 11th Int. Joint Conf. Artificial Intelligence, Vol. 89, San Mateo, CA, (Morgan Kaufmann, 1989), pp. 762–767. Google Scholar
12. D. Pham and D. Karaboga, Intelligent Optimisation Techniques: Genetic Algorithms, Tabu Search, Simulated Annealing and Neural Networks (Springer, 2012). Google Scholar
13. J. Zhang, J. Zhang, T. Lok and M. R. Lyu, Appl. Math. Comput. 185 (2) (2007) 1026. Web of Science, Google Scholar
14. P. G. Benardos and G. Vosniakos, Eng. Appl. Artif. Intell. 20 (3) (2007) 365. Crossref, Web of Science, Google Scholar
15. R. Kohavi et al., A study of cross-validation and bootstrap for accuracy estimation and model selection, Int. Joint Conf. Artificial Intelligence, Vol. 14, Stanford, CA, 1995, pp. 1137–1145. Google Scholar
16. J. S. Judd, Neural Network Design and the Complexity of Learning (MIT Press, 1990). Crossref, Google Scholar
17. M. Panella and G. Martinelli, Int. J. Circuit Theory Appl. 39 (1) (2011) 61. Crossref, Web of Science, Google Scholar
18. A. J. da Silva, T. B. Ludermir and W. R. de Oliveira, Neural Netw. 76 (2016) 55. Crossref, Web of Science, Google Scholar
19. A. J. da Silva and R. L. de Oliveira, Neural networks architecture evaluation in a quantum computer, 6th Brazilian Conf. Intelligent System, Uberlândia, MG (IEEE, 2017), pp. 163–168. Google Scholar
20. J. Biamonte, P. Wittek, N. Pancotti, P. Rebentrost, N. Wiebe and S. Lloyd, Nature 549 (7671) (2017) 195. Crossref, Web of Science, Google Scholar
21. M. Schuld, I. Sinayskiy and F. Petruccione, Quantum Inf. Process. 13 (11) (2014) 2567. Crossref, Web of Science, Google Scholar
22. A. W. Cross, L. S. Bishop, J. A. Smolin and J. M. Gambetta, Open quantum assembly language, arXiv:1707.03429. Google Scholar
23. C. A. Trugenberger, Phys. Rev. Lett. 87 (6) (2001) 067901. Crossref, Web of Science, Google Scholar
24. C. A. Trugenberger, Quantum Inf. Process. 1 (6) (2002) 471. Crossref, Web of Science, Google Scholar
25. T. Brun, H. Klauck, A. Nayak, M. Rötteler and Ch. Zalka, Phys. Rev. Lett. 91 (2003) 209801. Crossref, Web of Science, Google Scholar
26. M. Schuld, I. Sinayskiy and F. Petruccione, Quantum computing for pattern classification, Pacific Rim Int. Conf. Artificial Intelligence, (Springer, 2014), pp. 208–220. Crossref, Google Scholar
27. T. Menneer and A. Narayanan, Tech. Rep. R329 (1995). Google Scholar
28. B. Ricks and D. Ventura, Training a quantum neural network, Advances in Neural Information Processing Systems 16, S. Thrun, L. K. Saul and B. Schölkopf (eds.) (MIT Press, 2004), pp. 1019–1026. Google Scholar
29. I. Goodfellow, Y. Bengio, A. Courville and Y. Bengio, Deep Learning, Vol. 1 (MIT Press, Cambridge, 2016). Google Scholar
30. F. Pedregosa, G. Varoquaux, A. Gramfort, V. Michel, B. Thirion, O. Grisel, M. Blondel, P. Prettenhofer, R. Weiss, V. Dubourg, J. Vanderplas, A. Passos, D. Cournapeau, M. Brucher, M. Perrot and É. Duchesnayothers, J. Mach. Learn. Res. 12 (2011) 2825. Web of Science, Google Scholar
31. L. Prechelt, Proben1: A set of neural network benchmark problems and benchmarking rules, (1994). Google Scholar
32. D. Kingma and J. Ba, Adam: A method for stochastic optimization, arXiv:1412.6980. Google Scholar
33. V. Dunjko, J. M. Taylor and H. J. Briegel, Advances in quantum reinforcement learning, 2017 IEEE Int. Conf. Systems, Man, and Cybernetics (SMC) (IEEE, 2017), pp. 282–287. Google Scholar