# Bonn 2020 – wissenschaftliches Programm

# Die DPG-Frühjahrstagung in Bonn musste abgesagt werden! Lesen Sie mehr ...

## Bereiche | Tage | Auswahl | Suche | Aktualisierungen | Downloads | Hilfe

# T: Fachverband Teilchenphysik

## T 47: Neural networks and systematic uncertainties

### T 47.10: Vortrag

### Mittwoch, 1. April 2020, 18:45–19:00, H-HS IV

**Confronting EFT with artificial neural networks in the quest for physics beyond the Standard Model** — Alexander Grohsjean and •Jonas Rübenach — DESY, Hamburg, Germany

As no sign of physics beyond the Standard Model has emerged at the Large Hadron Collider so far, high precision measurements of particle properties and couplings become increasingly interesting. A commonly used language to interpret these measurements is effective field theory, in which higher-dimensional operators are added to the Standard Model. Traditional approaches most commonly set constraints on anomalous couplings by employing and combining unfolded measurements.

This talk introduces novel neural-network driven analysis methods to be used in conjunction with effective field theory. The neural networks learn from truth information of Monte Carlo simulation in order to directly perform hypothesis testing on measured data. These new methods outperform traditional approaches by providing stronger constraints of at least a factor of 5.