LHC Physics as Fun Data Science
- Kolloquium

LHC Physics as Fun Data Science
Modern machine learning is having significant impact on essentially all aspects of LHC physics. The simple reason is that LHC physics uniquely combines vast and highly complex data sets with precise first-principles predictions. I will introduce some ML-related aspects of LHC theory and show how we can benefit from new concepts and methods. This includes precision simulations including uncertainty estimates, inverted simulations and unfolding in a mathematically consistent manner, anomaly searches, and symbolic regression, to close the theory circle and return to formulas.



![3D visualisation of human neuronal tissue reconstructed by multi-scale X-ray phase contrast tomography. Neuronal cell nuclei are shown in yellow for the granule neurons in the dentate gyrus region of the hippocampus. Blood vessels are shown in red. By changing the X-ray optical magnification in the multi-scale recordings, one can zoom into regions-of-interest (red ovals). In these scans the resolution is high enough to resolve sub-structures of the nucleus, associated with different DNA packing regimes. Adapted from [6]](/storages/physik/_processed_/e/4/csm_Kolloquium_Salditt_0e30a3f090.png)




