A MATLAB-Based Study on the Realization and Approximation Performance of RBF Neural Networks


Article Preview

BP neural network is a kind of widely used feed-forward network. However its innate shortcomings are gradually giving rise to the study of other networks. Currently one of the research focuses in the area of feed-forward networks is radial basis function neural network. To test the radial basis function neural network for nonlinear function approximation capability, this paper first introduces the theories of RBF networks, as well as the structure, function approximation and learning algorithm of radial basis function neural network. Then a simulation test is carried out to compare BPNN and RBFNN. The simulation results indicate that RBFNN is simpler in structure, faster in speed and better in approximation performance. That is to say RBFNN is superior to BPNN in many aspects. But when solving the same problem, the structure of radial basis networks is more complicated than that of BP neural networks. Keywords: Radial basis function; Neural network; Function approximation; Simulation; MATLAB



Edited by:

Bale V. Reddy




S. Ding and X. H. Chang, "A MATLAB-Based Study on the Realization and Approximation Performance of RBF Neural Networks", Applied Mechanics and Materials, Vols. 325-326, pp. 1746-1749, 2013

Online since:

June 2013




[1] C.L.M. Harnold, K.Y. Lee. Free-model Based Adaptive Inverse Neuron controller for Dynamic Systems[C]. The 37th IEEE Conference on Decision and Control, Tampa, Florida, (1998), pp.507-512.

DOI: https://doi.org/10.1109/cdc.1998.760728

[2] Kalogirou, S.A. Artificial Neural Networks in Renewable Energy Systems Applications. Renew Energy Rev, May. 2001, pp.373-401.

[3] ZHI Hui-qiang, YANG Zeng-jun, TIAN Liang. A Comparative Study on BP Network and RBF Network in Function Approximation, [J]. Bulletin of Science and Technology, Vol. 21 (2005), pp.193-197.

[4] Liu Yong Zhang Liyi. Implementation of BP and RBF neural network and their performance comparison, [J]. Electronic Measurement Technology, Vol. 30 (2007), pp.77-80.

[5] Ramakrishnan, M&GM.VcluN.Prabadaran, K.Ekambaravanan, P.vivekanandan and P.Thangavelu. Function Approximation Using Feedforward Networks with Sigmoidal Signals, [J]. Information Journal of soft computing, Vol. 1 (2006), pp.76-82.

[6] Zhang wenjun, Albert Barrion. Function Approximation and Documentation of Sampling Data Using Artificial Neural Networks, [J]. Environmental Monitoring and Assessment, Vol. 122(2006), pp.185-201.

DOI: https://doi.org/10.1007/s10661-005-9173-6