Abstract
When the traditional rough neural network is structured, The selection of initial weights are random values between (0,1).This article address this issue, proposed an application of rough set theory attribute importance, replaced with the attribute importance method of initial weights. Finally, with instance validation, compared to the traditional rough neural network,This method is not only to accelerate the network convergence rate, but also enhances the adaptability of BP neural network.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Hai, J.: Neural network theory, pp. 191–209. Mechanism Industry Press, Beijing (2009)
Zhou, K., Kang, Y.: Neural network model and Matlab programmer, pp. 140–148. TsinghuaUniversity Press, Beijing (2004)
Wu, Y., Zhang, L.: The generalization ability of neural networks and structural optimization algorithm. Computer Science 19(6), 21–25 (2002)
Zhao, W., Huang, D., Ge, Y.: Application of genetic algorithms to the structure optimization of radial basis probabilistic neural networks. IEEE Transactions on Neural Networks 12(1), 1243–1246 (2002)
Pawlak, Z.: Rough Set-Theoretical Aspects of Reasoning about Data, pp. 9–30. Kluwer Academic Publishers, Dordrecht (1991)
Chen, W.C., Chang, N.B., Chen, J.C.: Rough set-based hybrid fuzzy-neural controner design for inudsrtial wastewater treatment. Water Resaerch 37(l), 95–107 (2003)
Wanfu, Z., Shijun, Z.: The Structural Optimization for Neural Network Based on Rough Sets. Computer Engineering and Design (9), 4210–4212 (2009)
Wang, H.: A Study on the Fusion of Granular Computing Based on Rough Set and Neural Networks. Computer Engineering and Design (8) (2010)
Liu, B.: The Research of Rough Set on Data Preprocessing; Baldonado, M., Chang, C.-C.K., Gravano, L., Paepcke, A., Liu, B.: The Research of Rough Set on Data Preprocessing. The Stanford Digital Library Metadata Architecture. Int. J. Digit. Libr. 1, 108–121 (1997)
Zhou, C.: Attribute reduction based on rough set. Hefei University of Technology (2008)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2011 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Liu, B., Hao, S. (2011). Optimal Design of Weigh for Networks Based on Rough Sets. In: Liu, B., Chai, C. (eds) Information Computing and Applications. ICICA 2011. Lecture Notes in Computer Science, vol 7030. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-25255-6_66
Download citation
DOI: https://doi.org/10.1007/978-3-642-25255-6_66
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-25254-9
Online ISBN: 978-3-642-25255-6
eBook Packages: Computer ScienceComputer Science (R0)