Exécution de notre outil de synthèse sur un nouvel article

Résumé : This chapter discusses some of the practical reasons data scientists may still think about deep learning when they build time series forecasting solutions. Specifically, it looks at the following important topics: reasons to add deep learning to readers' time series toolkit; recurrent neural networks for time series forecasting; and how to develop gated recurrent units and long short-term memories for time series forecasting. Deep learning is a subset of machine learning algorithms that learn to extract the features by representing input data as vectors and transforming them with a series of linear algebra operations into a given output. Deep learning neural networks are powerful engines capable of learning from arbitrary mappings from inputs to outputs, supporting multiple inputs and outputs, and automatically extracting patterns in input data that spans over long sequences of time.