TensorFlow has been widely used for many applications in machine learning and deep learning. However, TensorFlow is more than that, it is a general purpose computing library. Based on that, people have created a rich ecosystem for quickly developing models. In this talk, I will show how statisticians can get most of the main features in TensorFlow such as automatic differentiation, optimization, and Bayesian analysis through a simple linear regression example.
Hoang is on his final year of the PhD program in Statistics at Carlos III University of Madrid. He enjoys Bayesian inference and statistical computation. He contributes to several R packages in his repositories.