A New Method for Learning RBF Networks by Utilizing Singular Regions
The usual way to learn radial basis function (RBF) networks consists of two stages: first, select reasonable weights between input and hidden layers, and then optimize weights between hidden and output layers. When we learn multilayer perceptrons (MLPs), we usually employ the stochastic descent called backpropagation (BP) algorithm or 2nd-order methods such as pseudo-Newton method and conjugate gradient method. Recently new learning methods called singularity stairs following (SSF) methods have been proposed for learning real-valued or complex-valued MLPs by making good use of singular regions. SSF can monotonically decrease training error along with the increase of hidden units, and stably find a series of excellent solutions. This paper proposes a completely new method for learning RBF networks by introducing the SSF paradigm, and compares its performance with those of existing learning methods.
KeywordsNeural networks RBF networks Learning method Singular region Reducibility mapping
This work was supported by Grants-in-Aid for Scientific Research (C) 16K00342.
- 1.UCI Machine Learning Repository (1996). http://archive.ics.uci.edu/ml/
- 9.Satoh, S., Nakano, R.: Multilayer perceptron learning utilizing singular regions and search pruning. In: Proceedings of International Conference on Machine Learning and Data Analysis, pp. 790–795 (2013)Google Scholar
- 10.Satoh, S., Nakano, R.: A yet faster version of complex-valued multilayer perceptron learning using singular regions and search pruning. In: Proceedings of 7th International Joint Conference on Computational Intelligence (IJCCI), NCTA, vol. 3, pp. 122–129 (2015)Google Scholar