Ant Colony Algorithm Based on Improved Neural Network Algorithm and its Application

Abstract:

This paper mainly to the ant colony algorithm ant colony system (application pseudo-random proportional rules) and add adaptive learning, momentum BP algorithm of these three together was improved, established a hybrid algorithm, to a certain extent overcome the BP algorithm is easy to fall into local minimum value, slow convergence speed, and achieved satisfactory results. Generally speaking, the performance of BP network is composed of two components: the topology of the network and network learning algorithm. The topology of the network design especially hidden node number should be how to choose the number of neurons more reasonable there is no unified theory, the solution actual problem at present is more of the experience and the method of combining the test to determine the optimal number of hidden nodes. This paper mainly discussed the structure of neural network to determine later, network learning process problems.

• Periodical: Applied Mechanics and Materials (Volumes 543-547)
• Pages: 2116-2119
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.543-547.2116
• Online since: March 2014
• Authors: Qing Qing Zhang*, Qian Zhang, Yue Jiang Feng
• Keywords: Ant Colony Algorithm, Genetic Algorithm (GA), Improved Neural Networks

References

[1] M. Lovbjerg, T. Krink. Extending particle swarm op'mizxrs with self-organized critically. Proceeding IEEE Conference on Evolutionary Computation, 2002: 1588-1593.

DOI: 10.1109/cec.2002.1004479

[2] A. Ratnaweera, S.K. Halgamuge, H.C. Watson. Self-Organizing hierarchical particle swarm optimizer with time-varying acceleration coefficients. IEEE Trans. Evol. Comput., 2004, 8(3): 240一255.

DOI: 10.1109/tevc.2004.826071

[3] Trelea LC. The particle swarm optimization algorithm: convergence analysis and parameter selection. Information Processing Letters, 2003: 317-325.

DOI: 10.1016/s0020-0190(02)00447-7

[4] J.G. Digalakis, K.G. Margaritis. An experimental study of benchmarking functions for genetic algorithms. Intern. J. Computer Math, vo1. 79(4), 2002: 403-416.

DOI: 10.1080/00207160210939

[5] D.H. Ackley. A connectionist machine for genetic hillcimbing. Kluwer Academic Publishers, Boston, (1987).

[6] Martin T., Hagan, Howard B et al. Neural Network Design. New York: PWS Pr, (1996).

[7] F van den Bergh. An Analysis of Particle Swarm Optimizers. PhD thesis, Department of Computer Science, University of Pretoria, South Africa, (2002).

[8] Dan Lloyd. Functional MRI and the Study of Human Consciousness. Journal of Cognitive Neuroscience, 2002, 14: 818-831.

DOI: 10.1162/089892902760191027