Speaker
Description
A common thread of the ORIGINS is the presence of ever increasing data volumes both from instruments and simulation that simultaneously promise wealth of scientific insight. This data-intensive era, which often can only be managed in large scientific collaborations, coincides with a particularly interesting, but challenging phase in computing: While Machine Learning, particularly Deep Learning, has shown immense progress over the last decade, scientific applications have unique requirements regarding precision and interpretability and uncertainty quantification. At the same time general-purpose performance scaling is nearing an inflection point, which make both new algorithmic and infrastructure advances unavoidable. The Data Science viewpoint, that brings together Statistics, Machine Learning and Computing allows tackling these challenges in a cross-cutting manner. In this talk I'll discuss plans for the ORIGINS Data Science Lab and report on recent advances from the perspective of the experiments at the Large Hadron Collider such as the use of new ML techniques in the search for Beyond Standard Model Physics, advances in Open and FAIR Data and collaborative statistical modelling and new computing infrastructure for the exabyte era.
