On-line RBFNN based identification of rapidly time-varying nonlinear systems with optimal structure-adaptation. (English) Zbl 1038.68091
Summary: This paper presents an adaptive RBF network for the on-line identification and tracking of rapidly-changing time-varying nonlinear systems. The proposed algorithm is capable of maintaining the accuracy of learned patterns even when a large number of aged patterns are replaced by new ones through the adaptation process. Moreover, the algorithm exhibits a strong learning capacity with instant embodiment of new data which makes it suitable for tracking of fast-changing systems. However, the accuracy and speed in the adaptation is balanced by the computational cost which increases with the square of the number of the radial basis functions, resulting in a computational expensive, but still practically feasible, algorithm. The simulation results show the effectiveness (in terms of degradation of learned patterns and learning capacity) of this architecture for adaptive modeling.
MSC:
| 68T05 | Learning and adaptive systems in artificial intelligence |
References:
| [1] | Broomhead, D. S.; Lowe, D., Multivariable function interpolation and adaptive networks, Complex Syst., 2, 321-355 (1988) · Zbl 0657.68085 |
| [2] | Hartman, E. J.; Keeler, J. D.; Kowalski, J. M., Layered neural networks with Gaussian hidden units as universal approximators, Neural Comput., 2, 210-215 (1990) |
| [3] | Karayiannis, N. B., Reformulated radial basis neural networks trained by gradient descent, IEEE Trans. Neural Netw., 10, 3, 657-671 (1999) |
| [4] | Krzyzak, A.; Linder, T., Radial basis function networks and complexity regularization in function learning, IEEE Trans. Neural Netw., 9, 247-256 (1998) |
| [5] | C.T. Lin, Neural Fuzzy Control Systems with Structure and Parameter Learning, World Scientific, Singapore, 1994.; C.T. Lin, Neural Fuzzy Control Systems with Structure and Parameter Learning, World Scientific, Singapore, 1994. |
| [6] | Moody, J.; Darken, C. J., Fast learning in locally-tuned processing units, Neural Comput., 1, 281-294 (1989) |
| [7] | Niyogi, P.; Girosi, F., On the relationship between generalization error, hypothesis complexity, and sample complexity for radial basis functions, Neural Comput., 8, 819-842 (1996) |
| [8] | Park, D. C.; El-Sharkawi, M. A.; Marks, R. J., An adaptively trained neural network, IEEE Trans. Neural Netw., 2, 3, 334-345 (1991) |
| [9] | Park, J.; Sandberg, W., Universal approximation using radial-basis-function networks, Neural Comput., 3, 246-257 (1991) |
| [10] | Park, J.; Sandberg, I. W., Universal approximation and radial basis function networks, Neural Comput., 5, 305-316 (1993) |
| [11] | Ruiz de Angulo, V.; Torras, C., On-line learning with minimal degradation in feedforward networks, IEEE Trans. Neural Netw., 6, 3, 657-668 (1995) |
| [12] | S.G. Tzafestas, Y. Anthopoulos, Supervised learning in multilayer perceptrons: the back-propagation algorithm, in: S.G. Tzafestas (Ed.), Soft Computing in Systems and Control Technology, World Scientific, Singapore, 1999, pp. 3-30.; S.G. Tzafestas, Y. Anthopoulos, Supervised learning in multilayer perceptrons: the back-propagation algorithm, in: S.G. Tzafestas (Ed.), Soft Computing in Systems and Control Technology, World Scientific, Singapore, 1999, pp. 3-30. |
| [13] | Tzafestas, S. G.; Rigatos, G. G., Self tuning multivariable fuzzy and neural control using genetic algorithms, J. Inform. Optimiz. Sci., 21, 2, 257-287 (2000) · Zbl 0958.93055 |
| [14] | Tzafestas, S. G.; Skoundrianos, E. N.; Rigatos, G. G., Nonlinear neural control of discrete-time systems using local model neural networks, Int. J. Knowledge-Based Intell. Eng. Syst., 4, 2, 130-140 (2000) |
| [15] | S.G. Tzafestas, D. Vogiatzis, Concerning Hopfield networks: an overview with application to system identification and control, in: S.G. Tzafestas (Ed.), Computational Intelligence in Systems and Control Design and Applications, Kluwer, Dordrecht, 1999, pp. 311-334.; S.G. Tzafestas, D. Vogiatzis, Concerning Hopfield networks: an overview with application to system identification and control, in: S.G. Tzafestas (Ed.), Computational Intelligence in Systems and Control Design and Applications, Kluwer, Dordrecht, 1999, pp. 311-334. · Zbl 0936.93003 |
| [16] | Xu, L.; Krzyzak, A.; Yuille, A., On radial basis function nets and kernel regression: approximation ability, convergence rate and receptive field size, Neural Netw., 7, 609-628 (1994) · Zbl 0817.62031 |
| [17] | Yingwei, L.; Sundararajan, N.; Saratchandran, P., Identification of time-varying nonlinear systems using minimal radial basis function networks, IEE Proc. Control Theory Appl., 144, 2, 202-208 (1997) · Zbl 0875.93073 |
This reference list is based on information provided by the publisher or from digital mathematics libraries. Its items are heuristically matched to zbMATH identifiers and may contain data conversion errors. In some cases that data have been complemented/enhanced by data from zbMATH Open. This attempts to reflect the references listed in the original paper as accurately as possible without claiming completeness or a perfect matching.
