A reservoir radial-basis function neural network in prediction tasks

被引：3

作者：

Tyshchenko O.K. ^{[1
]}

机构：

[1] Control Systems Research Laboratory Kharkiv National University of Radio Electronics, 14 Lenin Ave., Kharkiv

来源：

Automatic Control and Computer Sciences | 2016年 / 50卷 / 02期

关键词：

computational intelligence; kernel function; learning procedure; radial-basis function neural network; time series prediction;

D O I：

10.3103/S0146411616020061

中图分类号：

学科分类号：

摘要：

A reservoir radial-basis function neural network, which is based on the ideas of reservoir computing and neural networks and designated for solving extrapolation tasks of nonlinear non-stationary stochastic and chaotic time series under conditions of a short learning sample, is proposed in the paper. The network is built with the help of a radial-basis function neural network with an input layer, which is organized in a special manner and a kernel membership function. The proposed system provides high approximation quality in terms of a mean squared error and a high convergence speed using the second-order learning procedure. A software product that implements the proposed neural network has been developed. A number of experiments have been held in order to research the system’s properties. Experimental results prove the fact that the developed architecture can be used in Data Mining tasks and the fact that the proposed neural network has a higher accuracy compared to traditional forecasting neural systems. © 2016, Allerton Press, Inc.

引用

页码：65 / 71

页数：6

共 15 条

[1]

Jaeger H., The Echo State Approach to Analyzing and Training Recurrent Neural Networks, (2001)

[2]

Maass W., Legenstein R.A., Markram H., A new approach towards vision suggested by biologically realistic neural microcircuit models, Proc. of the 2nd Workshop on Biologically Motivated Computer Vision, Lecture Notes in Computer Science, pp. 124-132, (2002)

[3]

Jaeger H., Short Term Memory in Echo State Networks, (2001)

[4]

Maass W., Natschlager T., Fading memory and kernel properties of generic cortical microcircuit models, J. Physiol., Orlando: Academic Press, 98, 4, pp. 315-330, (2004)

[5]

Jaeger H., Reservoir riddles: Suggestions for echo state network research, Proceedings of the International Joint Conference on Neural Networks, pp. 1460-1462, (2005)

[6]

Jaeger H., Adaptive nonlinear system identification with echo state networks, Adv. Neural Inf. Process. Syst., 15, 3, pp. 593-600, (2003)

[7]

Steil J.J., Online stability of backpropagation-decorrelation recurrent learning, Neurocomputing, 69, 7, pp. 642-650, (2006)

[8]

Wyffels F., Schrauwen B., Stroobandt D., Using reservoir computing in a decomposition approach for time series prediction, Proceedings of the European Symposium on Time Series Prediction, Amsterdam, pp. 149-158, (2008)

[9]

Park J., Sandberg I.W., Universal approximation using radial-basis-function networks, Neural Comput., 3, pp. 246-257, (1991)

[10]

Sunil E.V.T., Yung C.S., Radial basis function neural network for approximation and estimation of nonlinear stochastic dynamic systems, IEEE Trans. Neural Networks, 5, pp. 594-603, (1994)

← 1 2 →