Speaker
Description
The landscape of machine learning applications aiding the physics programme of LHCb is broad and expanding in preparation for the restart of data taking in 2021 and beyond. This talk aims to offer a broad overview of the machine learning solutions adopted at LHCb in the context of event reconstruction. Following the data acquisition and processing workflow at LHCb, machine learning applications in tracking, triggering and particle identification will be discussed. Furthermore, this talk will expand on the ongoing development of deep learning architectures employed in the context of calorimetric cluster reconstruction, leveraging the use of graph and convolutional neural networks. The lecture will conclude by providing an example of a deep-learning-driven approach to physics analysis and an outline of the more cutting-edge techniques currently under development to tackle the increased luminosity expected in LHCb's future upgrades.
Details
Blaise Raheem Delaney, Ms, Cambridge, UK
| Is this abstract from experiment? | Yes |
|---|---|
| Name of experiment and experimental site | LHCb, CERN |
| Is the speaker for that presentation defined? | Yes |
| Internet talk | Yes |
