综述：深度学习用于时间序列预测

标题

Deep Learning for Time-Series Analysis

作者

Gamboa John Cristian Borges

下载地址

https://arxiv.org/abs/1701.01887

发布时间

2017/1/7

摘要

In many real-world application, e.g., speech recognition or sleep stage
classification, data are captured over the course of time, constituting a
Time-Series. Time-Series often contain temporal dependencies that cause two
otherwise identical points of time to belong to different classes or predict
different behavior. This characteristic generally increases the difficulty of
analysing them. Existing techniques often depended on hand-crafted features
that were expensive to create and required expert knowledge of the field. With
the advent of Deep Learning new models of unsupervised learning of features for
Time-series analysis and forecast have been developed. Such new developments
are the topic of this paper: a review of the main Deep Learning techniques is
presented, and some applications on Time-Series analysis are summaried. The
results make it clear that Deep Learning has a lot to contribute to the field.

推荐理由

Mr-UC :

        这是一篇用深度学习解决时间序列数据的综述，从领域来说，语音、视频、格式化数据都是时间序列数据；从应用层面来说，可以进行预测未来的值、异常点的检测、进行分类等，在现实场景具有非常广泛的应用。这篇文章从构造深度神经网络常用网络、当前已发表论文的一些主要工作、进行建模、预测、分类的一些方法三个方面进行阐述，内容很全面，通过阅读会对使用深度学习处理时间序列数据有一个全面的认识。