Methodology for the Application of Deep Neural Networks in Searches for New Physics at Colliders and Statistical Interpretation of Expected Resultsстатья
Статья опубликована в журнале из списка Web of Science и/или Scopus
Дата последнего поиска статьи во внешних источниках: 10 апреля 2024 г.
Аннотация:Methods for the application of neural networks in searches for new physics in collider experiments are described. Mechanisms of selecting observables, optimizing hyperparameters, and constructing cascades of deep neural networks are considered. Methods for a statistical analysis of neural-network discriminants in theta and CombinedLimit packages with allowance for various uncertainties are presented.