A Novel Structure for Radial Basis Function Networks—WRBF
A novel structure for radial basis function networks is proposed. In this structure, unlike traditional RBF, we set some weights between input and hidden layer. These weights, which take values around unity, are multiplication factors for input vector and perform a linear mapping. Doing this, we increase free parameters of the network, but since these weights are trainable, the overall performance of the network is improved significantly. According to the new weight vector, we called this structure Weighted RBF or WRBF. Weight adjustment formula is provided by applying the gradient descent algorithm. Two classification problems used to evaluate performance of the new RBF network: letter classification using UCI dataset with 16 features, a difficult problem, and digit recognition using HODA dataset with 64 features, an easy problem. WRBF is compared with classic RBF and MLP network, and our experiments show that WRBF outperforms both significantly. For example, in the case of 200 hidden neurons, WRBF achieved recognition rate of 92.78% on UCI dataset while RBF and MLP achieved 83.13 and 89.25% respectively. On HODA dataset, WRBF reached 97.94% recognition rate whereas RBF achieved 97.14%, and MLP accomplished 97.63%.
KeywordsRadial basis Neural network RBF WRBF Classification Gradient descent
Unable to display preview. Download preview PDF.
- 1.Knudsen EI (1994) Supervised Learning in the Brain. J Neurosci 14(7): 3985–3997Google Scholar
- 4.da Silva AB, Rosa JLG (2011) Advances on criteria for biological plausibility in artificial neural networks: think of learning processes. In: International joint conference on neural networks, CaliforniaGoogle Scholar
- 9.Xiaohu L et al (2011) A new multilayer feedforward small-world neural network with its performances on function approximation. In: IEEE Int’l Conf. on computer science and automation engineering, pp 353–357Google Scholar
- 11.Bashkirov OA, Braverman EM, Muchnik IB (1964) Potential function algorithms networks for pattern recognition learning machines. Autom Remote Control, pp 629–631Google Scholar
- 12.Hojjatoleslami A, Sardo L, Kittler J (1997) An RBF based classifier for the detection of microcalcifications in mammograms with outlier rejection capability In: International conference on neural networks, pp 379–1384Google Scholar
- 13.Wang D et al (2002) Protein sequences classification using radial basis function (RBF) neural networks. In: 9’th international conference on neural information processing, Singapore, pp 764–769Google Scholar
- 17.King JL, Reznik L (2006) Topology selection for signal change detection in sensor networks: RBF vs. MLP. In: International joint conference on neural networks, pp 2529–2535Google Scholar
- 18.Polat G, Altun H (2007) Evalutation of performance of KNN, MLP and RBF classifiers in emotion detection problem. In: 15th conference on signal processing and communications applications, vol 1, pp 1–4Google Scholar
- 19.Haykin S (2009) Neural networks and learning machines, 3rd edn. Prentice-Hall, Upper Saddle RiverGoogle Scholar
- 20.Werbos PJ (1974) Beyond regression: new tools for prediction and analysis in the behavioral science. PhD thesis, Harvard UniversityGoogle Scholar
- 21.Parker DB (1982) Learning logic. Invention Report S81-64, File 1, Oce of Technology Licensing. Stanford UniversityGoogle Scholar
- 28.Sug H (2010) Generating better radial basis function network for large data set of census. Int J Softw Eng Appl 4(2): 15–22Google Scholar