论文标题
时间折叠的卷积神经网络，以预测序列
Temporally Folded Convolutional Neural Networks for Sequence Forecasting
论文作者
论文摘要
在这项工作中，我们提出了一种新的方法来利用卷积神经网络进行时间序列预测。具有空间维度的顺序数据的时间方向$ d = 1,2 $被民主视为时空$（D+1）$ - 维度卷积神经网络的输入。然后，后者将数据流从$ d +1 \降低到d $ dimensions，然后是犯罪元单元，该单元使用此信息来预测后续的时间步长。我们从经验上将这种策略与卷积LSTM和LSTM的表现分别在顺序MNIST和JSB合唱数据集上进行了比较。我们得出的结论是，暂时折叠的卷积神经网络（TFC）的表现可能胜过常规的复发策略。
In this work we propose a novel approach to utilize convolutional neural networks for time series forecasting. The time direction of the sequential data with spatial dimensions $D=1,2$ is considered democratically as the input of a spatiotemporal $(D+1)$-dimensional convolutional neural network. Latter then reduces the data stream from $D +1 \to D$ dimensions followed by an incriminator cell which uses this information to forecast the subsequent time step. We empirically compare this strategy to convolutional LSTM's and LSTM's on their performance on the sequential MNIST and the JSB chorals dataset, respectively. We conclude that temporally folded convolutional neural networks (TFC's) may outperform the conventional recurrent strategies.
