id	author	title	date	pages	extension	mime	words	sentences	flesch	summary	cache	txt
work_2z3fjxhcrfhefbagjvcl4iyogm	Nikolaos Kourentzes	Neural network ensemble operators for time series forecasting	2014	29	.pdf	application/pdf	9379	986	65	Neural Network Ensemble Operators for Time Series The combination of forecasts resulting from an ensemble of neural networks Keywords: Time Series, Forecasting, Ensembles, Combination, Mode Although the use of ensembles is nowadays accepted as the norm in forecasting with NNs (Crone et al., 2011), their performance is a function of how Furthermore, ensembles of both training initialisations and sampling (bagging) are used to investigate the performance of the operators. In either case, neural network ensembles created from multiple initialisations or from the application of the Bagging algorithm, require the use (2013) showed that combining models fitted on data sampled at different frequencies can achieve better forecasting accuracy at all forecasts by model selection, mean, median and mode ensembles are provided. neural networks, while the commonly used mean ensembles were often outperformed by exponential smoothing forecasts. An evaluation of neural network ensembles and model selection for time series prediction.	./cache/work_2z3fjxhcrfhefbagjvcl4iyogm.pdf	./txt/work_2z3fjxhcrfhefbagjvcl4iyogm.txt