mu2e Track Quality Selection in Python/Sklearn

Zoom Presentation Registration: https://fnal.zoom.us/j/9332915404?pwd=VS9ZRTJ4ZksvQmNrOHBnajF0TzhqZz09

Using a gradient boosted decision tree, we can improve momentum track quality selection on the mu2e tracker simulation data. Using a decision tree rather than an artificial neural network halves the training time and classification time. Eventually this machine learning model will be used in production to analyze real data.

Return to Main Poster Presentation

To enlarge the poster, double-click on the image.