Abstract
This paper presents a two-stage learning algorithm to reduce the hidden nodes of a radial basis function network (RBFN). The first stage involves the construction of an RBFN using the dynamic decay adjustment (DDA) and the second stage involves the use of a modified histogram algorithm (HIST) to reduce hidden neurons. DDA enables the RBFN to perform constructive learning without pre-defining the number of hidden nodes. The learning process of DDA is fast but it tends to generate a large network architecture as a result of its greedy insertion behavior. Therefore, an RBFNDDA-HIST is proposed to reduce the nodes. The proposed RBFNDDA-HIST is tested with three benchmark medical datasets. The experimental results show that the accuracy of the RBFNDDA-HIST is compatible with to that of RBFNDDA but with less number of nodes. This proposed network is favorable in a real environment because the computation cost can be reduced.
This is a preview of subscription content, log in via an institution to check access.
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
Meng Joo, E., Shiqian, W., Juwei, L.: Face recognition using radial basis function (RBF) neural networks. In: Proceedings of the 38th IEEE Conference on Decision and Control, vol. 3, pp. 2162–2167 (1999)
Moody, J., Darken, C.J.: Fast learning in networks of locally-tuned processing units. Neural Computation 1(2), 281–294 (1989)
Guang-Bin, H., Saratchandran, P., Sundararajan, N.: A generalized growing and pruning RBF (GGAP-RBF) neural network for function approximation. IEEE Transactions on Neural Networks 16(1), 57–67 (2005)
Kang, L., Jian-Xun, P., Er-Wei, B.: Two-stage mixed discrete-continuous identification of Radial Basis Function (RBF) Neural models for nonlinear systems. IEEE Transactions on Circuits and Systems I: Regular Papers 56(3), 630–643 (2009)
Freeman, J.A.S., Saad, D.: Learning and generalization in radial basis function networks. Neural Computation 7(5), 1000–1020 (1995)
Yu, H.: Network complexity analysis of multilayer feedforward artificial neural networks. In: Schumann, J., Liu, Y. (eds.) Appl. of Neural Networks in High Assur. Sys. SCI, vol. 268, pp. 41–55. Springer, Heidelberg (2010)
Zhang, G.P.: Avoiding pitfalls in neural network research. IEEE Transactions on Systems, Man, and Cybernetics, Part C: Applications and Reviews 37(1), 3–16 (2007)
Reed, R.: Pruning algorithms-a survey. IEEE Transactions on Neural Networks 4(5), 740–747 (1993)
Karnin, E.D.: A simple procedure for pruning back-propagation trained neural networks. IEEE Transactions on Neural Networks 1(2), 239–242 (1990)
Augasta, M.G., Kathirvalavakumar, T.: A novel pruning algorithm for optimizing feedforward neural network of classification problems. Neural Processing Letters 34(3), 241–258 (2011)
Ioannidis, Y.: The histogry of histogram. In: Proceedings of the 29th International Conference on Very Large Data Bases, vol. 29, pp. 19–30 (2003)
Legg, P.A., Rosin, P.L., Marshall, D., Morgan, J.E.: Improving accuracy and efficiency of registration by mutual information using Sturges’ histogram rule. In: Medical Image Understanding and Analysis, pp. 26–30 (2007)
Sietsma, J., Dow, R.J.F.: Neural net pruning-why and how. In: IEEE International Conference on Neural Networks, vol. 1, pp. 325–333 (1988)
Liang, X.: Removal of hidden neurons in multilayer perceptrons by orthogonal projection and weight crosswise propagation. Neural Computing and Applications 16(1), 57–68 (2007)
Zhang, Z., Qiao, J.: A node pruning algorithm for feedforward neural network based on neural complexity. In: 2010 International Conference on Intelligent Control and Information Processing (ICICIP), pp. 406–410 (2010)
Shimazaki, H., Shinomoto, S.: A method for selecting the bin size of a time histogram. Journal of Neural Computation 19(6), 1503–1527 (2007)
Asunction, A., Newman, D.J.: No Title. University of California, School of Information and Computer Science, Irvine, CA (2007)
Paetz, J.: Reducing the number of neurons in radial basis function networks with dynamic decay adjustment. Neurocomputing 62, 79–91 (2004)
Abbass, H.A.: An evolutionary artificial neural networks approach for breast cancer diagnosis. Artificial Intelligence in Medicine 25(3), 265–281 (2002)
Fogel, D.B., Wasson III, E.C., Boughton, E.M.: Evolving neural networks for detecting breast cancer. Cancer Letters 96(1), 49–53 (1995)
Abbass, H.A., Towsey, M., Finn, G.: C-Net: A method for generating non-deterministic and dynamic multivariate decision trees. Knowledge and Information Systems 3(2), 184–197 (2001)
Pylkkonen, J.: New pruning criteria for efficient decoding. In: Proceedings of the 9th European Conference on Speech Communication and Technology, pp. 581–584 (2005)
Steinbiss, V., Tran, B.H., Ney, H.: Improvement in beam search. In: International Conference on Spoken Language Processing, pp. 2143–2146 (1994)
Berthold, M.R., Diamond, J.: Constructive training of probabilistic neural networks. Neurocomputing 19, 167–183 (1998)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2014 Springer International Publishing Switzerland
About this paper
Cite this paper
Goh, P.Y., Tan, S.C., Cheah, W.P. (2014). A Nodes Reduction Procedure for RBFNDDA through Histogram. In: Loo, C.K., Yap, K.S., Wong, K.W., Teoh, A., Huang, K. (eds) Neural Information Processing. ICONIP 2014. Lecture Notes in Computer Science, vol 8834. Springer, Cham. https://doi.org/10.1007/978-3-319-12637-1_16
Download citation
DOI: https://doi.org/10.1007/978-3-319-12637-1_16
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-12636-4
Online ISBN: 978-3-319-12637-1
eBook Packages: Computer ScienceComputer Science (R0)