Artificial intelligence

Abstract: In this paper, we propose an approach to solving the problem of forecasting multivariate time series of telemetry data using ensemble neural networks. Approaches to the construction of neural network en-sembles are analyzed and accuracy of prediction is evaluated. It is studied a possibility of training the neural network ensembles for reducing errors of multivariate time series forecasting.

Keywords: Forecasting, artificial neural network, ensemble of neural networks, telemetry, multivari-ate time series

References: