Open AccessUSING LSTM NETWORK FOR SOLVING THE MULTIDIMENTIONAL TIME SERIES FORECASTING PROBLEM
Author(s) -
M. Obrubov,
Svetlana Kirillova
Publication year - 2021
Publication title -
nacionalʹnaâ associaciâ učënyh/nacionalʹnaâ associaciâ učenyh
Language(s) - English
Resource type - Journals
eISSN - 2782-2869
pISSN - 2413-5291
DOI - 10.31618/nas.2413-5291.2021.2.68.450
Subject(s) - series (stratigraphy) , computer science , artificial neural network , time series , artificial intelligence , hyperparameter , recurrent neural network , data mining , machine learning , paleontology , biology
The article discusses using of the recurrent neural networks technology to the multidimensional time series prediction problem. There is an experimental determination of the neural network architecture and its main hyperparameters carried out to achieve the minimum error. The revealed network structure going to be used further to detect anomalies in multidimensional time series.