Abstract 2: Novel Machine Learning Methods in High-Energy Physics This work introduces innovative semi-weakly supervised machine learning techniques for enhancing sensitivity to rare physics processes in collider experiments. By leveraging neural networks tailored to domain-specific features, the approach improves signal extraction and classification efficiency. Applications to simulated and real data demonstrate the effectiveness of these methods in uncovering subtle signatures of new physics phenomena.
Events
Abstract 2: Novel Machine Learning Methods in High-Energy Physics This work introduces innovative semi-weakly supervised machine learning techniques for enhancing sensitivity to rare physics processes in collider experiments. By leveraging neural networks tailored to domain-specific features, the approach improves signal extraction and classification efficiency. Applications to simulated and real data demonstrate the effectiveness of these methods in uncovering subtle signatures of new physics phenomena.