NATHANIEL HEY

Identification of highly boosted $H\to \gamma \gamma$ decays with the ATLAS detector using deep neural networks

This thesis introduces two jet tagging algorithms to identify highly boosted $H\to \gamma \gamma$ decays using the ATLAS detector at the LHC. Based on the Deep Neural Network (DNN) architecture, the first algorithm's performance is comparable to an existing algorithm designed for highly boosted $Z\to e^{+}{e}^{-}$ decays. The DNN jet tagger is also multifunctional and highly effective for identifying $Z\to e^{+}{e}^{-}$ decays. Notably, it displayed enhanced rejection rates for background $(\tau )\tau$-jets. The second algorithm leverages an Adversarial Neural Network (ANN) architecture for mass-decorrelated classification. While it exhibited a slight performance decrease compared to the DNN-based tagger, it demonstrated a $27.8\%$ reduction in mutual information between the mass feature and scalar discriminant metric, substantiating its capability for mass-decorrelated jet identification.