Paper Titles

Research on Modeling Virtual Battlefield Based-On Ontology
p.1749

A Modified Box-Counting Method to Estimate the Fractal Dimensions
p.1756

Research on Three-Dimensional Digitization Method of General Cliff Petroglyph in Lianyungang City
p.1762

Solution to the 0-1 Multidimensional Knapsack Problem Based on DNA Computation
p.1767

New Evolutionary Neural Network Based on Continuous Ant Colony Optimization
p.1773

Identifying Transformer Inrush Current Based on Artificial Neural Network
p.1779

A Research on Rapid Modeling Technique of Virtual Reality 3-Dimentional Underground Piping
p.1786

A Study of a New ELID Grinding Fluid by BP Neural Network Model
p.1792

Surface Fitting of Parametric Improvement Based on Original Points
p.1797

HomeApplied Mechanics and MaterialsApplied Mechanics and Materials Vols. 58-60New Evolutionary Neural Network Based on...

New Evolutionary Neural Network Based on Continuous Ant Colony Optimization

Article Preview

Abstract:

The evolutionary neural network can be generated combining the evolutionary optimization algorithm and neural network. Based on analysis of shortcomings of previously proposed evolutionary neural networks, combining the continuous ant colony optimization proposed by author and BP neural network, a new evolutionary neural network whose architecture and connection weights evolve simultaneously is proposed. At last, through the typical XOR problem, the new evolutionary neural network is compared and analyzed with BP neural network and traditional evolutionary neural networks based on genetic algorithm and evolutionary programming. The computing results show that the precision and efficiency of the new neural network are all better.

You might also be interested in these eBooks

Information Technology for Manufacturing Systems II

Info:

Periodical:

Applied Mechanics and Materials (Volumes 58-60)

Pages:

1773-1778

DOI:

https://doi.org/10.4028/www.scientific.net/AMM.58-60.1773

Citation:

Cite this paper

Online since:

June 2011

Authors:

Wei Gao

Keywords:

Ant Colony Optimization (ACO), BP Network, Evolutionary Neural Network

Export:

RIS, BibTeX

Price:

Permissions CCC:

Request Permissions

Permissions PLS:

Request Permissions

Сopyright:

© 2011 Trans Tech Publications Ltd. All Rights Reserved

Share:

Citation:

[1] X. Yao: Int. J. of Intelligent Systems Vol. 8 (1993), p.539.

[2] X. Yao: Int. J. of Neural Systems Vol. 4 (1993), p.203.

[3] H. Muhlenbein: Parallel Computing Vol. 14 (1990), p.249.

[4] S. Baluja: IEEE Trans. on SMC Vol. 26 (1996), p.450.

[5] A.N. Skourikhine, in: 7th Int. Conf. on EP'98, Springer, New York (1998), p.629.

[6] H. Takahashi, T. Agui and H. Nagahshi, in: Proc. Science of ANNⅡ, Orlando, Florido (1993), p.208.

[7] X. Yao and Y. Liu: IEEE Trans. on NN Vol. 8 (1997), p.694.

[8] J. Fang and Y.G. Xi: Artificial Intelligence in Engineering Vol. 11 (1997), p.155.

[9] V. Maniezzo: IEEE Trans. on NN Vol. 5 (1994), p.39.

[10] W. Gao, in: Proc. of ICLMC2003, IEEE, New York (2003), p.1287.

[11] F. Jin: Foundation of Neural Computation Intelligence—Principles and Methods (Southwest Jiaotong University Press, Chengdu 2000).

[12] M. Dorigo, V. Maniezzo and A. Colorni: IEEE Trans. on SMC Vol. 26 (1996), p.29.

[13] M. Dorigo and G. Di Caro, in: New Ideas in Optimization, McGraw-Hill, London (1999), p.11.

[14] M. Dorigo and T. Stutzle: Ant Colony Optimization (MIT Press, Cambridge 2004).

[15] N. Monmarché, G. Venturimi and M. Slimane: Future Generation Computer System Vol. 16 (2000), p.937.

[16] M. Mohit, B.K. Sachin and P. Sidhartha, et al: Ind. Eng. Chem. Res. Vol. 39 (2000), p.3814.

[17] J. Dréo and P. Siarry: Future Generation Computer Systems Vol. 20 (2004), p.841.

[18] W. Gao, in: Proc. of the ICNC2007, IEEE, New York (2007), p.792.