OPTIMIZATION OF LSTM NETWORKS FOR TIME SERIES FORECASTING

Background. LSTM neural networks are a very promising means to develop time series analysis and forecasting. However, as well as neural networks for other fields and applications, LSTM networks have a lot of architecture versions, training parameters, and hyperparameters, whose inappropriate select...

詳細記述

書誌詳細

第一著者:	Vadim V. Romanuke
フォーマット:	Artigo
言語:	Inglês
出版事項:	Igor Sikorsky Kyiv Polytechnic Institute 2021-12-01
シリーズ:	KPI Science News
主題:	time series forecasting LSTM network LSTM layer size forecasting accuracy root-mean-square error maximum absolute error
オンライン･アクセス:	http://scinews.kpi.ua/article/view/230989
タグ:	タグ追加 タグなし, このレコードへの初めてのタグを付けませんか!