论文标题
零射击和少量时间的时间序列预测，序列回归复发性神经网络
Zero-shot and few-shot time series forecasting with ordinal regression recurrent neural networks
论文作者
论文摘要
经常性的神经网络（RNN）是几个顺序学习任务的最先进，但是它们通常需要大量数据才能良好地概括。对于许多时间序列预测（TSF）任务，在培训时可能只有几十个观察结果，这限制了此类模型的使用。我们提出了一个基于RNN的新型模型，该模型通过在许多量化时间序列的空间中学习嵌入共享功能来直接解决此问题。我们展示了这如何使我们的RNN框架准确，可靠地预测未看到的时间序列，即使几乎没有可用的培训数据。
Recurrent neural networks (RNNs) are state-of-the-art in several sequential learning tasks, but they often require considerable amounts of data to generalise well. For many time series forecasting (TSF) tasks, only a few dozens of observations may be available at training time, which restricts use of this class of models. We propose a novel RNN-based model that directly addresses this problem by learning a shared feature embedding over the space of many quantised time series. We show how this enables our RNN framework to accurately and reliably forecast unseen time series, even when there is little to no training data available.
