Self-Organizing Maps in High Energy Physics

Abstract The Self-Organizing-Map (SOM) is a widely used neural network for dimensional reduction and clustering. It has yet to find its use in high energy physics. This paper discusses two applications of SOM: first, we map regions with relative content rare process ( H → WW *). Second obtain Monte Carlo normalization factors different physics processes by fitting the dimensionally reduced representation. Analysis training are performed on ATLAS open data.