Fourier Series Chaotic Neural Networks
Chaotic neural networks have been proved to be strong tools to solve the optimization problems. In order to escape the local minima, a new chaotic neural network model called Fourier series chaotic neural network was presented. The activation function of the new model is non-monotonous, which is composed of sigmoid and trigonometric function. First, the figures of the reversed bifurcation and the maximal Lyapunov exponents of single neural unit were given. Second, the new model is applied to solve several function optimizations. Finally, 10-city traveling salesman problem is given and the effects of the non-monotonous degree in the model on solving 10-city traveling salesman problem are discussed. Seen from the simulation results, the new model we proposed is more effective.
KeywordsChaotic neural network Fourier series Trigonometric function
Unable to display preview. Download preview PDF.
- 2.Hopfield, J.: Neural Networks and Physical Systems with Emergent Collective Computational Abilities. In: Proc. Natl. Acad. Sci., vol. 79, pp. 2554–2558 (1982)Google Scholar
- 3.Xu, Y., Sun, M., Duan, G.: Wavelet Chaotic Neural Networks and Their Application to Optimization Problems. In: Adi, A., Stoutenburg, S., Tabet, S. (eds.) RuleML 2005. LNCS, vol. 3791, pp. 379–384. Springer, Heidelberg (2005)Google Scholar
- 7.Wang, L.: Intelligence optimization algorithm and its application. Press of TUP (2001)Google Scholar