Investigation Into the Viability of Neural Networks as a Means for Anomaly Detection in Experiments Like Atlas at the LHC
This addresses the challenge of efficiently finding rare events in petabytes of data from particle physics experiments, which is incremental as it applies existing methods to a specific domain.
The paper investigates the use of neural networks for anomaly detection in high-energy physics experiments like ATLAS at the LHC to identify rare events in large datasets, using Monte Carlo simulated data to evaluate different architectures.
Petabytes of data are generated at the Atlas experiment at the Large Hadron Collider however not all of it is necessarily interesting, so what do we do with all of this data and how do we find these interesting needles in an uninteresting haystack. This problem can possibly be solved through the process of anomaly detection. In this document, Investigation Into the Viability of Neural Networks as a Means for Anomaly Detection in Experiments Like Atlas at the LHC the effectiveness of different types of neural network architectures as anomaly detectors are researched using Monte Carlo simulated data generated by the DarkMachines project. This data is meant to replicate Standard Model and Beyond Standard Model events. By finding an effective model, the Atlas experiment can become more effective and fewer interesting events will be lost.