Speaker
Tony Menzo
Description
We present the recent and ongoing developments with respect to the use of machine learning methods in models of hadronization as implemented in general purpose event generators. Specifically we focus on the performance of generative machine learning algorithms in reproducing Pythia-simulated hadronization kinematics and global observables. Finally, we will discuss the inclusion of error estimates within the machine-learning-based hadronization pipeline and progress in implementing a machine-learning-improved model of hadronization.
| Submitted on behalf of a Collaboration? | Yes |
|---|
