Advertisement

The Research on Controlling the Iteration of Quantum-Inspired Evolutionary Algorithms for Artificial Neural Networks

  • Fengmao Lv
  • Guowu Yang
  • Shuangbao Wang
  • Fuyou Fan
Part of the Lecture Notes in Computer Science book series (LNCS, volume 8546)

Abstract

From recent research on optimizing artificial neural networks (ANNs), quantum-inspired evolutionary algorithm (QEA) was proved to be an effective method to design an ANN with few connections and high classifications. Quantum-inspired evolutionary neural network (QENN) is a kind of evolving neural networks. Similar to other evolutionary algorithms, it is important to control the iteration of QENN, otherwise it will waste a lot of time when QENN has been convergent. This paper proposes an appropriate termination criterion to control the iteration of QENN. The proposed termination criterion is based on the probability of the best solution. Experiments about pattern classification on iris have been done to demonstrate the effectiveness and applicability of the termination criterion. The results show that the termination criterion proposed in this paper could control the iteration of QENN effectively and save a mass of computing time by decreasing the number of generations of QENN.

Keywords

Q-bit representation quantum-inspired evolutionary algorithms (QEA) quantum-inspired evolutionary neural network (QENN) termination criterion convergence 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Angeline, P.J., Saunders, G.M., Pollack, J.B.: An evolutionary algorithm that constructs recurrent neural networks. IEEE Transactions on Neural Networks 5(1), 54–65 (1994)CrossRefGoogle Scholar
  2. 2.
    Bäck, T., Schwefel, H.P.: An overview of evolutionary algorithms for parameter optimization. Evolutionary Computation 1(1), 1–23 (1993)CrossRefGoogle Scholar
  3. 3.
    Belew, R.K., McInerney, J., Schraudolph, N.N.: Evolving networks: Using the genetic algorithm with connectionist learning. Citeseer (1990)Google Scholar
  4. 4.
    Brown, M., Harris, C.J.: Neurofuzzy adaptive modelling and control. Prentice-Hall (1994)Google Scholar
  5. 5.
    Han, K.H., Kim, J.H.: Genetic quantum algorithm and its application to combinatorial optimization problem. In: Proceedings of the 2000 Congress on Evolutionary Computation, vol. 2, pp. 1354–1360. IEEE (2000)Google Scholar
  6. 6.
    Han, K.H., Kim, J.H.: Quantum-inspired evolutionary algorithm for a class of combinatorial optimization. IEEE Transactions on Evolutionary Computation 6(6), 580–593 (2002)CrossRefGoogle Scholar
  7. 7.
    Han, K.H., Kim, J.H.: Quantum-inspired evolutionary algorithms with a new termination criterion, H ε gate, and two-phase scheme. IEEE Transactions on Evolutionary Computation 8(2), 156–169 (2004)CrossRefGoogle Scholar
  8. 8.
    Kitano, H.: Designing neural networks using genetic algorithms with graph generation system. Complex Systems Journal 4, 461–476 (1990)zbMATHGoogle Scholar
  9. 9.
    Kwok, T.Y., Yeung, D.Y.: Constructive algorithms for structure learning in feedforward neural networks for regression problems. IEEE Transactions on Neural Networks 8(3), 630–645 (1997)CrossRefGoogle Scholar
  10. 10.
    Leung, F.H.F., Lam, H.K., Ling, S.H., Tam, P.K.S.: Tuning of the structure and parameters of a neural network using an improved genetic algorithm. IEEE Transactions on Neural Networks 14(1), 79–88 (2003)CrossRefGoogle Scholar
  11. 11.
    Lu, T.C., Yu, G.R., Juang, J.C.: Quantum-based algorithm for optimizing artificial neural networks. IEEE Transactions on Neural Networks 24(8), 1266–1278 (2013)CrossRefGoogle Scholar
  12. 12.
    Oong, T.H., Isa, N.A.M.: Adaptive evolutionary artificial neural networks for pattern classification. IEEE Transactions on Neural Networks 22(11), 1823–1836 (2011)CrossRefGoogle Scholar
  13. 13.
    Parekh, R., Yang, J., Honavar, V.: Constructive neural-network learning algorithms for pattern classification. IEEE Transactions on Neural Networks 11(2), 436–451 (2000)CrossRefGoogle Scholar
  14. 14.
    Platel, M.D., Schliebs, S., Kasabov, N.: Quantum-inspired evolutionary algorithm: a multimodel eda. IEEE Transactions on Evolutionary Computation 13(6), 1218–1232 (2009)CrossRefGoogle Scholar
  15. 15.
    Reed, R.: Pruning algorithms-a survey. IEEE Transactions on Neural Networks 4(5), 740–747 (1993)CrossRefGoogle Scholar
  16. 16.
    Schaffer, J.D., Whitley, D., Eshelman, L.J.: Combinations of genetic algorithms and neural networks: A survey of the state of the art. In: International Workshop on Combinations of Genetic Algorithms and Neural Networks, COGANN 1992, pp. 1–37. IEEE (1992)Google Scholar
  17. 17.
    Sexton, R.S., Dorsey, R.E., Johnson, J.D.: Toward global optimization of neural networks: a comparison of the genetic algorithm and backpropagation. Decision Support Systems 22(2), 171–185 (1998)CrossRefGoogle Scholar
  18. 18.
    Tsai, J.T., Chou, J.H., Liu, T.K.: Tuning the structure and parameters of a neural network by using hybrid taguchi-genetic algorithm. IEEE Transactions on Neural Networks 17(1), 69–80 (2006)CrossRefGoogle Scholar
  19. 19.
    Yao, X.: A review of evolutionary artificial neural networks. International Journal of Intelligent Systems 8(4), 539–567 (1993)CrossRefGoogle Scholar
  20. 20.
    Yao, X.: Evolving artificial neural networks. Proceedings of the IEEE 87(9), 1423–1447 (1999)CrossRefGoogle Scholar
  21. 21.
    Yao, X., Liu, Y.: A new evolutionary system for evolving artificial neural networks. IEEE Transactions on Neural Networks 8(3), 694–713 (1997)CrossRefMathSciNetGoogle Scholar
  22. 22.
    Zhang, R., Gao, H.: Improved quantum evolutionary algorithm for combinatorial optimization problem. In: 2007 International Conference on Machine Learning and Cybernetics, vol. 6, pp. 3501–3505. IEEE (2007)Google Scholar

Copyright information

© Springer International Publishing Switzerland 2014

Authors and Affiliations

  • Fengmao Lv
    • 1
  • Guowu Yang
    • 1
  • Shuangbao Wang
    • 1
  • Fuyou Fan
    • 1
  1. 1.School of Computer Science and EngineeringUniversity of Electronic Science and Technology of ChinaChengduP.R. China

Personalised recommendations