Abstract
This paper presents a new minimum classification error (MCE)–mean square error (MSE) hybrid cost function to enhance the classification ability and speed up the learning process of radial basis function (RBF)-based classifier. Contributed by the MCE function, the proposed cost function enables the RBF-based classifier to achieve an excellent classification performance compared with the conventional MSE function. In addition, certain learning difficulties experienced by the MCE algorithm can be solved in an efficient and simple way. The presented results show that the proposed method exhibits a substantially higher convergence rate compared with the MCE function.
Similar content being viewed by others
References
Zhang GP (2000) Neural networks for classification: a survey. IEEE Trans Syst Man Cybern Part C 4:451–462
Girosi F, Poggio T (1990) Networks and the best approximation property. Biol Cybern 63:169–176
Poggio T, Girosi F (1990) Regularization algorithms for learning that are equivalent to multiplayer networks. Science 247:978–982
Haykin S (1999) Neural networks: a comprehensive foundation. Prentice Hall, New Jersey
Bishop C (1995) Neural networks for pattern recognition. Clarendon Press, Oxford
Howell AJ, Buxton H (1998) Learning identity with radial basis function networks. Neurocomputing 20:15–34
Ceccarelli M, Hounsou JT (1996) Sequence recognition with radial basis function networks: experiments with spoken digits. Neurocomputing 11:75–88
Schwenker F, Kestler HA, Palm G (2001) Three learning phases for radial-basis-function networks. Neural Netw 14:439–458
Rumelhart DE, Durbin R, Golden R, Chauvin Y (1995) Bachpropagation: the basic theory. In: Chauvin Y, Rumelhart DE (eds) Backpropagation: theory, architectures, and application. LEA, Hillsdale, pp 1–34
Lampariello F, Sciandrone M (2001) Efficient training of RBF neural networks for pattern recognition. IEEE Trans Neural Netw 12(5):1235–1242
Juang B-H, Katagiri S (1992) Discriminative learning for minimum error classification. IEEE Trans Signal Process 40(12):3043–3054
Watanabe H, Yamaguchi T, Katagiri S (1997) Discriminative metric design for robust pattern recognition. IEEE Trans Pattern Anal Mach Intell 45(11):2655–2662
Holmes CC, Mallick BK (1998) Bayesian radial basis function of variable dimension. Neural Comput 10:1217–1233
Kohonen T (1997) Self-organizing maps. Springer, Berlin Heidelberg New York
Kubat M (1998) Decision trees can initialize radial-basis function networks. IEEE Trans Neural Netw 9:813–821
Scholkopf B, Sung KK (1997) Comparing support vector machine with Gaussian kernels to radial basis function classifiers. IEEE Trans Signal Process 45:2758–2765
Available at http://www.openresource.com/openres/archives/P/AIR.shtml
Lang KJ, Witbrock MJ (1998) Learning to tell two spirals apart. In: Proceedings of the 1988 connectionist models summer school. Morgan Kaufmann, San Mateo
Fahlman SE, Lebiere C (1990) The cascade correlation learning architecture. In: Toursky DS (ed) Advances in neural information processing system 2. Morgan Kaufmann, San Mateo
Lengelle R, Denoeux T (1996) Training MLPS layer by layer using an objective function for internal representations. Neural Netw 2(1):83–97
Garavaglia SB (1999) The two spirals benchmark: lessons from the hidden layers. Int Jt Conf Neural Netw 2:1158–1163
Available at http://www.ics.uci.edu/∼mlearn/MLRepository.html
Katagiri S, Juang BH, Lee CH (1998) Pattern recognition using a family of design algorithms based upon the generalized probabilistic descent method. Proc IEEE 86(11):2345–2373
Sito W, Chow TWS (2004) Induction machine fault detection: using SOM-based RBF neural networks. IEEE Trans Ind Electron 51(1):183–194
Chow TWS, Hai S (2004) Induction machine fault diagnostic analysis with wavelet analysis. IEEE Trans Ind Electron 51(3):558–565
Chow TWS, Tan HZ (2000) HOS-based nonparametric and parametric methodologies for machine fault detection. IEEE Trans Ind Electron 47(5):1051–1059
Chow TWS, Fei G (1995) Three phase induction machines asymmetrical fault identification using bispectrum. IEEE Trans Energy Convers 10(4):688–693
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Huang, D., Chow, T.W.S. Improving the effectiveness of RBF classifier based on a hybrid cost function. Neural Comput & Applic 16, 395–405 (2007). https://doi.org/10.1007/s00521-006-0063-9
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00521-006-0063-9