Echo in a small-world reservoir: Time-series prediction using an economical recurrent neural network

2017 ◽  
Author(s):  
Yuji Kawai ◽  
Tatsuya Tokuno ◽  
Jihoon Park ◽  
Minoru Asada
Keyword(s):  
Neural Network ◽  
Time Series ◽  
Recurrent Neural Network ◽  
Time Series Prediction ◽  
Small World

Time Series Prediction Method Based on Variant LSTM Recurrent Neural Network

2020 ◽  
Vol 52 (2) ◽  
pp. 1485-1500
Author(s):  
Jiaojiao Hu ◽  
Xiaofeng Wang ◽  
Ying Zhang ◽  
Depeng Zhang ◽  
Meng Zhang ◽  
...  
Keyword(s):  
Neural Network ◽  
Time Series ◽  
Recurrent Neural Network ◽  
Time Series Prediction ◽  
Prediction Method

scholarly journals A Dual-Stage Attention-Based Recurrent Neural Network for Time Series Prediction

2017 ◽  
Author(s):  
Yao Qin ◽  
Dongjin Song ◽  
Haifeng Chen ◽  
Wei Cheng ◽  
Guofei Jiang ◽  
...  
Keyword(s):  
Neural Network ◽  
Time Series ◽  
Recurrent Neural Network ◽  
Empirical Studies ◽  
Time Series Prediction ◽  
Attention Mechanism ◽  
Time Step ◽  
Narx Models ◽  
Dual Stage ◽  
Hidden States

The Nonlinear autoregressive exogenous (NARX) model, which predicts the current value of a time series based upon its previous values as well as the current and past values of multiple driving (exogenous) series, has been studied for decades. Despite the fact that various NARX models have been developed, few of them can capture the long-term temporal dependencies appropriately and select the relevant driving series to make predictions. In this paper, we propose a dual-stage attention-based recurrent neural network (DA-RNN) to address these two issues. In the first stage, we introduce an input attention mechanism to adaptively extract relevant driving series (a.k.a., input features) at each time step by referring to the previous encoder hidden state. In the second stage, we use a temporal attention mechanism to select relevant encoder hidden states across all time steps. With this dual-stage attention scheme, our model can not only make predictions effectively, but can also be easily interpreted. Thorough empirical studies based upon the SML 2010 dataset and the NASDAQ 100 Stock dataset demonstrate that the DA-RNN can outperform state-of-the-art methods for time series prediction.

Time Series Prediction Using Recurrent Neural Network

2019 ◽  
Vol 21 (4) ◽  
pp. 1771-1779
Author(s):  
JongHwa Kim ◽  
Jong Hoo Choi ◽  
Changwan Kang
Keyword(s):  
Neural Network ◽  
Time Series ◽  
Recurrent Neural Network ◽  
Time Series Prediction
Sign in / Sign up

Export Citation Format

Share Document