Transformer Models for Symbolic Calculations of Squared Amplitudes in HEP

In particle physics, a cross section is a measure of the likelihood that particles will interact or scatter with one another when they collide. It is a fundamental quantity and its computation can become time intensive. This project aims to apply state-of-the-art machine learning techniques, particularly transformer-based models, for the generation of symbolic representations of the squared amplitudes in HEP. The proposed sequence-to-sequence system aims to improve upon the existing time-intensive processes of calculations of the squared amplitude . By harnessing the power of transformers, this project seeks to optimize the process of converting symbolic amplitudes to squared representations.