论文信息 - A First Approximation to the Effects of Classical Time Series Preprocessing Methods on LSTM Accuracy

A First Approximation to the Effects of Classical Time Series Preprocessing Methods on LSTM Accuracy

A convenient data preprocessing has proven to be crucial in order to achieve high levels of accuracy, time series being no exception. For this kind of forecasting tasks, several specialized preprocessing methods have been described, being trend analysis and seasonal analysis some of them. Several have been formally grouped around a methodology that is always applied to state of the art time series forecasting models, like the well known ARIMA.

Francisco Charte | Antonio J. Rivera | Daniel Trujillo Viedma | María José del Jesus Díaz

[1] Gwilym M. Jenkins,et al. Time series analysis, forecasting and control , 1972 .

[2] Jürgen Schmidhuber,et al. LSTM: A Search Space Odyssey , 2015, IEEE Transactions on Neural Networks and Learning Systems.

[3] Jürgen Schmidhuber,et al. Framewise phoneme classification with bidirectional LSTM and other neural network architectures , 2005, Neural Networks.

[4] Yoshua Bengio,et al. Gradient Flow in Recurrent Nets: the Difficulty of Learning Long-Term Dependencies , 2001 .

[5] Wei-Min Shen,et al. Data Preprocessing and Intelligent Data Analysis , 1997, Intell. Data Anal..

[6] Jürgen Schmidhuber,et al. Learning to Forget: Continual Prediction with LSTM , 2000, Neural Computation.

[7] Rob J Hyndman,et al. Automatic Time Series Forecasting: The forecast Package for R , 2008 .

[8] PAUL J. WERBOS,et al. Generalization of backpropagation with application to a recurrent gas market model , 1988, Neural Networks.

[9] Dimitris Kanellopoulos,et al. Data Preprocessing for Supervised Leaning , 2007 .

[10] Jürgen Schmidhuber,et al. Deep learning in neural networks: An overview , 2014, Neural Networks.

[11] Jürgen Schmidhuber,et al. Long Short-Term Memory , 1997, Neural Computation.