Gauss Wavelet Chaotic Neural Networks

  • Yao-qun Xu
  • Ming Sun
  • Ji-hong Shen
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4232)


Chaotic neural networks have been proved to be powerful tools to solve the optimization problems. In order to escape the local minima, a new chaotic neural network model called Gauss Wavelet chaotic neural network was presented, and the chaotic mechanism is introduced by the attenuation of the self-feedback connection weight. The activation function of the new model is non-monotonous, which is composed of sigmoid function and Gauss Wavelet function. First, the figures of the reversed bifurcation and the maximal Lyapunov exponents of single neural unit were given. Second, the new model was applied to solve function optimizations. Finally, 10-city traveling salesman problem was given and the effects of the non-monotonous degree in the model on solving 10-city traveling salesman problem were discussed. The new model can solve the optimization problems more effectively because Gauss wavelet is a kind of basic function. Seen from the simulation results, the new model is powerful than the common chaotic neural network.


Global Minimum Solve Optimization Problem Maximal Lyapunov Exponent Chaotic Neural Network Function Optimization Problem 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Hopfield, J.J., Tank, D.W.: Neural Computation of Decision in Optimization Problems. Biol. Cybern. 52, 141–152 (1985)MATHMathSciNetGoogle Scholar
  2. 2.
    Hopfield, J.: Neural Networks and Physical Systems with Emergent Collective Computational Abilities. Proc. Natl. Acad. Sci. 79, 2554–2558 (1982)CrossRefMathSciNetGoogle Scholar
  3. 3.
    Xu, Y.-q., Sun, M., Duan, G.-r.: Wavelet Chaotic Neural Networks and Their Application to Optimization Problems. LNCS, vol. 3791, pp. 379–384. Springer, Heidelberg (2006)Google Scholar
  4. 4.
    Xu, Y.-q., Sun, M.: Gauss-Morlet-Sigmoid Chaotic Neural Networks. In: Huang, D.-S., Li, K., Irwin, G.W. (eds.) ICIC 2006. LNCS, vol. 4113, pp. 115–125. Springer, Heidelberg (2006)CrossRefGoogle Scholar
  5. 5.
    Xu, Y.-q., Sun, M., Shen, J.-h.: Gauss Chaotic Neural Networks. In: Yang, Q., Webb, G. (eds.) PRICAI 2006. LNCS (LNAI), vol. 4099, pp. 319–328. Springer, Heidelberg (2006)CrossRefGoogle Scholar
  6. 6.
    Potapove, A., Kali, M.: Robust chaos in neural networks. Physics Letters A 277(6), 310–322 (2000)CrossRefMathSciNetGoogle Scholar
  7. 7.
    Shuai, J.W., Chen, Z.X., Liu, R.T., et al.: Self-evolution Neural Model. Physics Letters A 221(5), 311–316 (1996)CrossRefGoogle Scholar
  8. 8.
    Chen, L., Aihara, K.: Chaotic Simulated Annealing by a Neural Network Model with Transient Chaos. Neural Networks 8(6), 915–930 (1995)CrossRefGoogle Scholar
  9. 9.
    Ling, W.: Intelligence optimization algorithm and its application. Press of TUP (2001)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Yao-qun Xu
    • 1
  • Ming Sun
    • 1
  • Ji-hong Shen
    • 2
  1. 1.Institute of System EngineeringHarbin University of CommerceHarbinChina
  2. 2.Dept. of MathematicsHarbin Engineering UniversityHarbinChina

Personalised recommendations