Data, ML models, and documentation for the use of the HEP community
Showcase of Resourses
Click on a box to go to the corresponding details
NPand Observables in b to c
Resources for NP analysis of b to c Observables
If you use these, please cite the related paper from the connected inspireHEP repository below.
Example Mathematica file- The example Mathematica notebook (.nb) in the repo. contains detailed examples to use the data-sets and the trained Self-normalizing neural networks (SNNs) for predictions for 3 types of observable combinations. It will be regularly updated for some time.
Data-sets- The repository contains both training and test data-sets for training any ML model.
SNN- It also contains trained SNNs for classification and regression of the connected datasets, in various formats like WLNet (Wolfram Language) and JSon (MXNet).
ResourceData- All of the above resources will be shortly available together as a Wolfram Language 'ResourceObject', directly downloadable and installable from within a Mathematica installation. Please check this space for updates.