Noise Detection Using Generative Adversarial Networks with Applications to High Energy Physics

In this project, we investigate the application of Generative Adversarial Networks (GANs) in signal processing to detect noise within large datasets, with a specific focus on their application to data processing for the Compact Muon Solenoid (CMS) experiment at CERN. GANs are employed to generate realistic signal representations and effectively distinguish between noise and true signals. We explore various GAN variants and data preprocessing techniques to optimize noise detection. The research showcases GANs' potential to enhance data reliability in high-energy physics experiments like CMS, contributing to improved particle physics analysis and discovery potential.