循环神经网络
单变量
系列(地层学)
计算机科学
时间序列
缺少数据
序列(生物学)
多元统计
人工智能
机器学习
计量经济学
人工神经网络
统计
数学
生物
遗传学
古生物学
作者
Yagmur Gizem Cinar,Hamid Mirisaee,Parantapa Goswami,Éric Gaussier,Ali Aït-Bachir
标识
DOI:10.1016/j.neucom.2018.05.090
摘要
Recurrent neural networks (RNNs) recently received considerable attention for sequence modeling and time series analysis. Many time series contain periods, e.g. seasonal changes in weather time series or electricity usage at day and night time. Here, we first analyze the behavior of RNNs with an attention mechanism with respect to periods in time series and illustrate that they fail to model periods. Then, we propose an extended attention model for sequence-to-sequence RNNs designed to capture periods in time series with or without missing values. This extended attention model can be deployed on top of any RNN, and is shown to yield state-of-the-art performance for time series forecasting on several univariate and multivariate time series.
科研通智能强力驱动
Strongly Powered by AbleSci AI