Optimization of ANN Based on EA

Hong Guo Zhu; Hai Xin; Chang Wen Zheng

doi:10.4028/www.scientific.net/AMR.271-273.629

Paper Titles

INS-Assisted GNSS Signal Tracking Modeling and Assessment
p.603

Mended EKF-Based GPS/INS Tight Coupling Simulator
p.609

Real Time Neural Network Control of a Twin Rotor System
p.616

Reserch on Enviroment of Embedded Software Testing
p.622

Optimization of ANN Based on EA
p.629

Web-Based Virtual Workplace Environment for Improving Safety
p.633

Feature Based Similarity Measures of 3D Models
p.639

Analysis on Effectiveness of Intelligent Transport Systems on National Highways
p.645

Analysis on an Effect from the Build-up of Incident Management System
p.651

HomeAdvanced Materials ResearchAdvanced Materials Research Vols. 271-273Optimization of ANN Based on EA

Optimization of ANN Based on EA

Abstract:

Artificial neural network (ANN) and evolutionary algorithm (EA) are both biology-based models of information processing. The basic theories of ANN and EA are described. Then the mechanisms of using EA for ANN’s optimization are explained and the research states are summarized. The existing problems and future directions are demonstrated finally.

You might also be interested in these eBooks

View Preview

Info:

Periodical:

Advanced Materials Research (Volumes 271-273)

Pages:

629-632

DOI:

https://doi.org/10.4028/www.scientific.net/AMR.271-273.629

Citation:

Cite this paper

Online since:

July 2011

Authors:

Hong Guo Zhu, Hai Xin, Chang Wen Zheng

Keywords:

Artificial Neural Network (ANN), Evolutionary Algorithm (EA), Optimization

Export:

RIS, BibTeX

Price:

Permissions CCC:

Request Permissions

Permissions PLS:

Request Permissions

Сopyright:

Citation:

References

[1] I. K . Nikolos, et al.: UAV Path Planning Using Evolutionary Algorithms, Studies in Computation Intelligence, Vol. 70(2007), pp.77-111.

Google Scholar

[2] Montana D. J, David L.: Training Feedforward Neural Networks Using Genetic Algorithm, Proc. Of 11th IJCAI, San Mateo(1989), pp.762-767.

Google Scholar

[3] P. J. Angeline, G. M. Saunders, and J. B. Pollack: An evolutionary algorithm that constructs recurrent neural networks, IEEE Trans. Neural Netw., Vol. 5(1994), pp.54-64.

DOI: 10.1109/72.265960

Google Scholar

[4] J. R. McDonnell and D. Waagen: Neural network structure design by evolutionary programming, in: Proc. 2nd Annu. Conf. Evolutionary Programming(1993), p.79–89.

Google Scholar

[5] D. B. Fogel: Using evolutionary programming to create neural networks that are capable of playing tic-tac-toe, in: Proc. Amer. Power Conf. (1993), p.875–879.

DOI: 10.1109/icnn.1993.298673

Google Scholar

[6] N. Garcia-Pedrajas, C. Hervas-Martinez, and J. Munoz-Perez, Covnet: A cooperative coevolutionary model for evolving artificial neural networks, IEEE Trans. Neural Netw., Vol. 14(2003), p.575–596.

DOI: 10.1109/tnn.2003.810618

Google Scholar

[7] X. Yao and Y. Liu: A new evolutionary system for evolving artificial neural networks, IEEE Trans. Neural Netw., Vol. 8(1997), p.694–713.

DOI: 10.1109/72.572107

Google Scholar

[8] X. Yao and Y. Liu: Making use of populations information in evolutionary artificial networks, IEEE Trans. Syst., Man, Cybern. B, Cybern., Vol. 28(1998), p.417–425.

DOI: 10.1109/3477.678637

Google Scholar

[9] Paulito P. Palmes elt.: Evolution and adaptation of neural networks，Proceedings of the International Joint Conference on Neural Networks, Vol. 1(2003), p.478－483.

DOI: 10.1109/ijcnn.2003.1223393

Google Scholar

[10] Paulito P. Palmes elt.: Mutation-based Genetic Neural Network, IEEE Transactions on Neural Networks, Vol. 16(2005), p.587－600.

DOI: 10.1109/tnn.2005.844858

Google Scholar