A Performance Comparison of Chaotic Simulated Annealing Models for Solving the N-queen Problem
Chaotic neural network models employing two chaotic simulated annealing (CSA) schemes, one with decaying self-couplings and the other with a decaying time-step, are used to solve the N-queen problem. Their optimisation performances are compared in terms of feasibility, efficiency, robustness and scalability in a two-parameter domain chosen for each model. Computational results show that the decaying self-coupling approach offers better feasibility, robustness and scalability, with efficiency being comparable for the two models. Correlation between feasibility and efficiency illustrates some chaotic search characteristics common to both models.
KeywordsTravelling Salesman Problem Constraint Satisfaction Problem Hopfield Neural Network Chaotic Neural Network Hopfield Network
Unable to display preview. Download preview PDF.
- Nozawa, H., (1994). Solution of the Optimization Problem Using the Neural Network Model as a Globally Coupled Map. Towards the Harnessing of Chaos, pp. 99-114.Google Scholar
- Yamada, T., Aihara, K., Kotani, M., (1993). Chaotic Neural Networks and The Travelling Salesman Problem. Proc. 1993 Int. Joint Conf. Neural Networks, Vol. 2, pp. 1549–1552.Google Scholar
- Hasegawa, M., Ikeguchi, T., Matozaki, T., Aihara, K., (1997). An Analysis on Additive Effects of Nonlinear Dynamics for Combinatorial Optimization. IEICE Trans. Fundamentals, Vol. E80-A, Iss. 1, pp. 206–213.Google Scholar
- Kwok, T., Smith, K. and Wang, L., (1998). Solving Combinatorial Optimization Problems by Chaotic Neural Networks. Intelligent Engineering Systems Through Artificial Neural Networks: Neural Networks, Fuzzy Logic, Evolutionary Programming, Data Mining, and Rough Sets, vol. 8. C. Dagli et al (eds.), pp. 317-322.Google Scholar
- Wang, L., Smith, K., (1998). Chaos in the Discretized Analog Hopfield Neural Network and Potential Applications to Optimization. Proc. Int. Conf. Neural Networks, pp. 1679-1684.Google Scholar
- Kwok, T., Smith, K., Wang, L., (1998). Incorporating Chaos into the Hopfield Neural Network for Combinatorial Optimization. 1998 World Multiconference on Systemics, Cybernetics and Informatics, Vol. 1, pp. 659–665.Google Scholar
- Tagliarini, G. A., Page, E. W., (1987). Solving Constraint Satisfaction Problems with Neural Networks. Proc. IEEE Int. Conf. Neural Networks, III-741 — III-747.Google Scholar
- Takefuji, Y., Szu, H., (1989). Design of Parallel Distributed Cauchy Machines. Proc. IJCNN, I-529-I-532.Google Scholar
- Akiyama, Y., Yamashita, A., Kajiura, M., Aiso, H., (1989). Combinatorial Optimization with Gaussian Machines. IJCNN, Vol. 1, pp. I–533–I–540.Google Scholar