# Generative Neural Network Models for Fast Particle Shower Simulation in Calorimeters for Geant4

- Institution: CERN
- Department: CERN openlab Summer Student Programme 2024
- Speaker: Mohammed Touami
- Year: 2024
- Language: English
- Subjects: Physics
- Source: [CERN](https://videos.cern.ch/record/3014082)
- Licence: [CERN](http://copyright.web.cern.ch)
- Who can watch: Tweens profiles and older (sources give no ratings; placed by Invisible Network from the source's own words)

The extensive program of high-energy physics experiments relies on Monte Carlo simulation. Simulation can be used for testing hypotheses of the underlying distribution of the data. The need for fast and large-scale simulated samples for HEP experiments motivates the development of new simulation techniques, particularly those based on neural network models. Machine-learning models are studied mainly in the context of fast shower simulation, as calorimeters are typically the most time-consuming detectors to simulate. Both accuracy and performance need to be validated before their implementation in production software. The project will focus on improving the accuracy of the fast shower simulation, studying the difference between different machine-learning solutions focusing on the low energy particle showers..

0:00:00 Slide 1

0:04:02 Slide 2

0:05:21 Slide 3

0:08:42 Slide 4

0:09:59 Slide 5

## Lectures

1. [Generative Neural Network Models for Fast Particle Shower Simulation in Calorimeters for Geant4](https://invisiblenetwork.ai/learn/cern/3014082/880259a7a654), 12 min (CERN's player)