π€ π Edge#57: Transformer Architectures for Time Series
TheSequence is the best way to build and reinforce your knowledge about machine learning and AI
In this issue:
we discuss transformers for time-series and Google Researchβs Temporal Fusion Transformers (TFT) in particular;Β
we learn how Uber manages uncertainty in time-series prediction models;Β
we explore tsfresh β a magical library for feature extraction in time-series datasets.
Enjoy the learning!