Deep Learning for Time Series Forecasting
In Chapter 11, we covered machine learning techniques for time series forecasting. In this chapter, we will focus on deep learning (a subset of machine learning), given promising research into its effectiveness, particularly when working with large sequences due to its ability to extract sophisticated patterns with minimal manual intervention. The rapid adoption of deep learning in general, for example, in computer vision (CV) and natural language processing (NLP), has been accelerated by techniques such as transfer learning, which leverages pretrained models to save significant development and training time.
Deep learning adapts well to both structured and unstructured data and can be applied to supervised, unsupervised, and semi-supervised learning tasks. In Chapter 13, you will explore using deep learning models in an unsupervised setting for outlier detection. In this chapter, the focus will be on supervised learning techniques.
...
