• Developed deep learning algorithms to study lost energy momentum in TTbar events for the detection of dark matter, one of the Standard Model Problems in physics.
• The project aims to predict and reconstruct anomalies below the signal region that are difficult to observe.
• Utilized a special type of Neural Network, called the Wasserstein Generative Adversarial Network-Gradient Penalty (WGAN-GP), to achieve the project objectives.
• Focused on the search for missing transverse energy and kinematic distributions for charged leptons and jets, which are subatomic particles.
• Discovered a correlation between Monte Carlo simulations used to detect particles and WGAN-GP signals that extract the distribution of signals produced under missing energy.
• The project aims to predict and reconstruct anomalies below the signal region that are difficult to observe.
• Utilized a special type of Neural Network, called the Wasserstein Generative Adversarial Network-Gradient Penalty (WGAN-GP), to achieve the project objectives.
• Focused on the search for missing transverse energy and kinematic distributions for charged leptons and jets, which are subatomic particles.
• Discovered a correlation between Monte Carlo simulations used to detect particles and WGAN-GP signals that extract the distribution of signals produced under missing energy.