Forecasting with deep neural networks. A time series is a sequence of values ordered in time. So, it needs to be transformed for supervised learning. By Vitor Cerqueira.
In the article you will learn:
- Supervised learning with time series
- Auto-regression with deep learning
- Hands-on
- Univariate time series
- From a sequence of values into a matrix
- From a matrix into a 3-d structure for deep learning
- Multivariate Time Series
Deep learning is increasingly relevant in time series applications. In this article, we explored how to transform a time series for deep learning. The input to traditional machine learning algorithms is a matrix. But, neural networks such as LSTMs work with three-dimensional data sets. So, time series need to be transformed from a sequence into this format. Nice one!
[Read More]