Tampere University of Technology

TUTCRIS Research Portal

Training Radial Basis Function Neural Networks for Classification via Class-specific Clustering

Research output: Contribution to journalArticleScientificpeer-review


Original languageEnglish
Pages (from-to)2458-2471
JournalIEEE Transactions on Neural Networks and Learning Systems
Issue number12
Early online date2015
Publication statusPublished - Dec 2016
Publication typeA1 Journal article-refereed


In training radial basis function neural networks (RBFNNs), the locations of Gaussian neurons are commonly determined by clustering. Training inputs can be clustered on a fully unsupervised manner (input clustering), or some supervision can be introduced, for example, by concatenating the input vectors with weighted output vectors (input-output clustering). In this paper, we propose to apply clustering separately for each class (class-specific clustering). The idea has been used in some previous works, but without evaluating the benefits of the approach. We compare the class-specific, input, and input-output clustering approaches in terms of classification performance and computational efficiency when training RBFNNs. To accomplish this objective, we apply three different clustering algorithms and conduct experiments on 25 benchmark data sets. We show that the class-specific approach significantly reduces the overall complexity of the clustering, and our experimental results demonstrate that it can also lead to a significant gain in the classification performance, especially for the networks with a relatively few Gaussian neurons. Among other applied clustering algorithms, we combine, for the first time, a dynamic evolutionary optimization method, multidimensional particle swarm optimization, and the class-specific clustering to optimize the number of cluster centroids and their locations.


  • Radial Basis Function Neural Networks , Classification, Class-specific Clustering

Publication forum classification

Field of science, Statistics Finland