Artificial intelligence

Abstract: In the article, the main forecasting methods are described and a new algorithm based on the group method of data handling and artificial neural networks is offered. The algorithm has been tested on the real data and has shown the better results, as compared with neural networks. The experimental dependence of a mean square prediction error, obtained with the use of the offered algorithm and neural networks, on the number of points in the training set is also found.

Keywords: forecasting, neural networks, GMDH, smoothing.

References: