IN2P3/IRFU Machine Learning workshop

Towards probabilistic models for capturing uncertainty

22 janv. 2020, 16:55

25m

Amphi (CC-IN2P3)

ML for data reduction : Application of Machine Learning to data reduction, reconstruction, building/tagging of intermediate object

Orateur

Alexandre Boucaud (APC / IN2P3)

Description

Many applications of machine learning in physics are currently limited by their lack of uncertainty propagation and estimation through the model. Such limitation can partly be overcome by shifting to the use of probabilistic models, which provide an output distribution instead of single values.
I will show an example of such shift on image processing in astrophysics.

Documents de présentation

Towards probabilistic models for capturing uncertainty-ML@IN2P3-jan2020.pdf

Towards probabilistic models to capture model uncertainty