Median radial basis function neural network
- 1 November 1996
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Neural Networks
- Vol. 7 (6) , 1351-1364
- https://doi.org/10.1109/72.548164
Abstract
Radial basis functions (RBFs) consist of a two-layer neural network, where each hidden unit implements a kernel function. Each kernel is associated with an activation region from the input space and its output is fed to an output unit. In order to find the parameters of a neural network which embeds this structure we take into consideration two different statistical approaches. The first approach uses classical estimation in the learning stage and it is based on the learning vector quantization algorithm and its second-order statistics extension. After the presentation of this approach, we introduce the median radial basis function (MRBF) algorithm based on robust estimation of the hidden unit parameters. The proposed algorithm employs the marginal median for kernel location estimation and the median of the absolute deviations for the scale parameter estimation. A histogram-based fast implementation is provided for the MRBF algorithm. The theoretical performance of the two training algorithms is comparatively evaluated when estimating the network weights. The network is applied in pattern classification problems and in optical flow segmentation.Keywords
This publication has 31 references indexed in Scilit:
- Motion estimation via cluster matchingPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1994
- Minimal Topology for a Radial Basis Functions Neural Network for Pattern ClassificationDigital Signal Processing, 1994
- Rival penalized competitive learning for clustering analysis, RBF net, and curve detectionIEEE Transactions on Neural Networks, 1993
- On the training of radial basis function classifiersNeural Networks, 1992
- Universal Approximation Using Radial-Basis-Function NetworksNeural Computation, 1991
- A Resource-Allocating Network for Function InterpolationNeural Computation, 1991
- A general regression neural networkIEEE Transactions on Neural Networks, 1991
- Layered Neural Networks with Gaussian Hidden Units as Universal ApproximationsNeural Computation, 1990
- Variants of self-organizing mapsIEEE Transactions on Neural Networks, 1990
- Fast Learning in Networks of Locally-Tuned Processing UnitsNeural Computation, 1989