Speaker
Description
Current studies of the hadron spectrum are limited by the accuracy and consistency of datasets. Information derived from theory models often requires fits to points at specific values of kinematic variables, which needs interpolation between measured points. In sparse data sets the quantification of uncertainties is problematic.
Machine Learning is a powerful tool that can be used to build an interpolated dataset, with quantification of uncertainties. The primary focus here is one type of machine learning called a Gaussian Process (GP). By calculating the covariance between known datapoints, the GP can predict the mean and standard deviation of other, unknown, datapoints. The model built here is checked and tested using Legendre polynomials to ensure it is unbiased and gives accurate predictions. This is then demonstrated on two datasets; one sparsely and one densely populated.
Whilst this model is only demonstrated on polarisation observables, it could easily be adapted to provide information on other measured quantities, such as cross-sections.
