A modified RBF network with application to system identification

Proposes a modified RBF network in which the regression weights are used to replace the constant weights in the output layer. It is shown that the modified RBF network can reduce the number of hidden units significantly. Moreover, the authors develop a computationally efficient algorithm, known as the EM algorithm, to estimate the parameters of the regression weights. A salient feature of this algorithm is that it decouples a complicated multiparameter optimization problem into L separate small-scale optimization problems, where L is the number of hidden units. The superior performance the modified RBF network over the standard RBF network is illustrated by means of a system identification example.

[1]  Gwilym M. Jenkins,et al.  Time series analysis, forecasting and control , 1972 .

[2]  M. J. D. Powell,et al.  Radial basis functions for multivariable interpolation: a review , 1987 .

[3]  Liang Wang,et al.  Complex systems modeling via fuzzy logic , 1996, IEEE Trans. Syst. Man Cybern. Part B.

[4]  D. Rubin,et al.  Maximum likelihood from incomplete data via the EM - algorithm plus discussions on the paper , 1977 .

[5]  Shang-Liang Chen,et al.  Orthogonal least squares learning algorithm for radial basis function networks , 1991, IEEE Trans. Neural Networks.

[6]  R. Shumway,et al.  AN APPROACH TO TIME SERIES SMOOTHING AND FORECASTING USING THE EM ALGORITHM , 1982 .

[7]  Tohru Katayama,et al.  Parameter identification for noisy image via the EM algorithm , 1990 .

[8]  R. Redner,et al.  Mixture densities, maximum likelihood, and the EM algorithm , 1984 .

[9]  David S. Broomhead,et al.  Multivariable Functional Interpolation and Adaptive Networks , 1988, Complex Syst..

[10]  F. Girosi,et al.  Networks for approximation and learning , 1990, Proc. IEEE.

[11]  Robert A. Jacobs,et al.  Hierarchical Mixtures of Experts and the EM Algorithm , 1993, Neural Computation.

[12]  D. Broomhead,et al.  Radial Basis Functions, Multi-Variable Functional Interpolation and Adaptive Networks , 1988 .

[13]  Ehud Weinstein,et al.  Parameter estimation of superimposed signals using the EM algorithm , 1988, IEEE Trans. Acoust. Speech Signal Process..

[14]  John Moody,et al.  Fast Learning in Networks of Locally-Tuned Processing Units , 1989, Neural Computation.