AN Improved RBF Neural Network Model Based on Hybrid Learning Algorithm

Zhao Hu Deng; Yan Qin Zhang

doi:10.4028/www.scientific.net/AMR.718-720.2202

Paper Titles

Virtual Walk-Through of Dunhuang Panorama-Based on Web
p.2175

A Simplified 3D Reconstruction Technique for Tomographic Particle Image Velocimetry
p.2184

A Fuzzy-Based Dynamic Load Decision Making Scheme in Cloud Computing
p.2191

A Wonderful Property and the Corresponding Demonstration about Magic Square of Odd Order
p.2197

AN Improved RBF Neural Network Model Based on Hybrid Learning Algorithm
p.2202

Design of a Multi-P3-AT-Robot Platform Using Ad Hoc Network
p.2208

Construction of Adolescent Digital Reading Assessment
p.2214

The Relationship between Online Reading Literacy and ICT Familiarity for Junior High School Students
p.2221

The Research of Graph Compression
p.2228

HomeAdvanced Materials ResearchAdvanced Materials Research Vols. 718-720AN Improved RBF Neural Network Model Based on...

AN Improved RBF Neural Network Model Based on Hybrid Learning Algorithm

Abstract:

When building the radial basis function (RBF) neural network with traditional method, the property of the network is easily influenced by the distribution of training samples. The learning ability and generalization ability are hard to achieve the optimum. In this paper, it presents a new method to solve this problem. In the method it replaced the traditional clustering algorithms with genetic algorithms to optimize the distribution of RBF. At the same time it combined the steepest descent method with GA to solve the binary defect of GA encoding. After experiments the results showed that the constructed neural network has a better architecture and more accuracy than that built with traditional method.

You might also be interested in these eBooks

View Preview

Info:

Periodical:

Advanced Materials Research (Volumes 718-720)

Pages:

2202-2207

DOI:

https://doi.org/10.4028/www.scientific.net/AMR.718-720.2202

Citation:

Cite this paper

Online since:

July 2013

Authors:

Zhao Hu Deng, Yan Qin Zhang

Keywords:

Niche, Optimization, RBF, Steepest Descent Method

Export:

RIS, BibTeX

Price:

Permissions CCC:

Request Permissions

Permissions PLS:

Request Permissions

Сopyright:

Citation:

References

[1] Sultan Noman Qasem, Siti Mariyam Shamsuddin. Hybrid Learning Enhancement of RBF Network Based on Particle Swarm Optimization. 6th International Symposium on Neural Networks, ISNN 2009, Proceedings, : 19-29.

DOI: 10.1007/978-3-642-01513-7_3

Google Scholar

[2] Liu, Y., Zheng, Q., Shi, Z., Chen, J.: Training Radial Basis Function Networks with Particle Swarms. In: Yin, F.-L., Wang, J., Guo, C. (eds.) ISNN 2004. LNCS, vol. 3173,: 317–322. Springer, Heidelberg (2004).

DOI: 10.1007/978-3-540-28647-9_54

Google Scholar

[3] Min Han, Wei Guo, Yunfeng Mu. A Modified RBF Neural Network in Pattern Recognition.Proceedings of International Joint Conference on Neural Networks, Orlando, Florida, USA, August 12-17, 2007.

DOI: 10.1109/ijcnn.2007.4371356

Google Scholar

[4] Ding S (2010) Artificial intelligence. Tsinghua University Press, Beijing.

Google Scholar

[5] Min Han, Wei Guo, etl. A Modified RBF Neural Network in Pattern Recognition. Proceedings of International Joint Conference on Neural Networks, Orlando, Florida, USA, August 12-17, 2007 : 2527-2532.

DOI: 10.1109/ijcnn.2007.4371356

Google Scholar

[6] Shifei Ding, Li XuAn, etl. Optimizing method of RBF neural network based on genetic algorithm. Neural Computation & Application, 2012 (21): 333–336.

DOI: 10.1007/s00521-011-0702-7

Google Scholar