Published on March 10, 2019 by

TensorFlow Probability (TFP) is a Python library built on TensorFlow that makes it easy to combine probabilistic models and deep learning on modern hardware (TPU, GPU). It’s for data scientists, statisticians, and ML researchers/practitioners who want to encode domain knowledge to understand data and make predictions with uncertainty estimates. In this talk we focus on the “layers” module and demonstrate how TFP “distributions” fit naturally with Keras to enable estimating aleatoric and/or epistemic uncertainty.

See the revamped dev site →

Watch all TensorFlow Dev Summit ’19 sessions →
Event homepage →

Subscribe to the TensorFlow YouTube channel →

Josh Dillon, Software Engineer

Music by Terra Monk →
Event Photo Album →

Category Tag