Structure Perturbation Optimization for Hopfield-Type Neural Networks

  • Gang Yang
  • Xirong Li
  • Jieping Xu
  • Qin Jin
Part of the Lecture Notes in Computer Science book series (LNCS, volume 8681)


In this paper, we extract the core idea of state perturbation from Hopfield-type neural networks and define state perturbation formulas to describe the general way of optimization methods. Departing from the core idea and the formulas, we propose a novel optimization method related to neural network structure, named structure perturbation optimization. Our method can produce a structure transforming process to retrain Hopfield-type neural networks to get better problem-solving ability. Experiments validate that our method effectively helps Hopfield-type neural networks to escape from local minima and get superior solutions.


stochastic noise structure perturbation Hopfield-type neural network maximum clique problem 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Cheng, K., Lin, J., Mao, C.: The application of competitive Hopfield neural network to medical image segmentation. IEEE Trans. Med. Imag. 15, 560–567 (1996)CrossRefGoogle Scholar
  2. 2.
    Van Den, D.E., Miller III, T.K.: Improving the Performance of the Hopfield-Tank Neural Network Through Normalization and Annealing. Biol. Cybern. 139, 129–139 (1989)Google Scholar
  3. 3.
    Singh, Y.: Dynamic Tunneling Based Regularization in Feedforward Neural Networks. Artificial Intell 131, 55–71 (2001)CrossRefzbMATHGoogle Scholar
  4. 4.
    Wang, L.P., Li, S., Tian, F.Y.: A Noisy Chaotic Neural Network for Solving Combinatorial Optimization Problems: Stochastic Chaotic Simulated Annealing. IEEE Trans. Syst. Man Cybern B Cybern. 34(5), 2119–2125 (2004)CrossRefGoogle Scholar
  5. 5.
    He, Y.Y.: Chaotic Simulated Annealing with Decaying Chaotic Noise. IEEE Trans. Neural Netw. 13(6), 1526–1531 (2002)Google Scholar
  6. 6.
    Chen, S.S.: Chaotic simulated annealing by a neural network with a variable delay: design and application. IEEE Trans. Neural Netw. 22(10), 1557–1565 (2011)Google Scholar
  7. 7.
    Tatem, A.J., Lewis, H.G., Atkinson, P.M., Nixon, M.S.: Super-Resolution Land Cover Pattern Prediction Using a Hopfield Neural Network. Remote Sensing of Environment 79, 1–14 (2002)CrossRefGoogle Scholar
  8. 8.
    Sun, M., Zhao, L., Cao, W., Xu, Y.Q., Dai, X.F., Wang, X.X.: Novel hysteretic noisy chaotic neural network for broadcast scheduling problems in packet radio networks. IEEE Trans. Neural Netw. 21(9), 1422–1433 (2010)Google Scholar
  9. 9.
    Yang, G., Yi, J.Y.: Dynamic characteristic of a multiple chaotic neural network and its application. Soft Comput. 17(5), 783–792 (2013)CrossRefGoogle Scholar
  10. 10.
    Chen, L., Aihara, K.: Chaotic simulated annealing by a neural network model with transient chaos. Neural Networks 8(6), 915–930 (1995)CrossRefGoogle Scholar
  11. 11.
    Karandashev, I., Kryzhanovsky, B.: The Mix-Matrix Method in the Problem of Binary Quadratic Optimization. In: Villa, A.E.P., Duch, W., Érdi, P., Masulli, F., Palm, G. (eds.) ICANN 2012, Part I. LNCS, vol. 7552, pp. 41–48. Springer, Heidelberg (2012)CrossRefGoogle Scholar

Copyright information

© Springer International Publishing Switzerland 2014

Authors and Affiliations

  • Gang Yang
    • 1
  • Xirong Li
    • 1
  • Jieping Xu
    • 1
  • Qin Jin
    • 1
  1. 1.Multimedia Computing Lab, School of InformationRenmin University of ChinaBeijingChina

Personalised recommendations