Deep Learning for Time-Series Analysis
It addresses the problem of analyzing time-series data with temporal dependencies for applications like speech recognition, but it is incremental as it reviews existing methods.
This paper reviews deep learning techniques for time-series analysis, highlighting their ability to learn features automatically and reduce reliance on hand-crafted methods, with results indicating significant contributions to the field.
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.