This repository is intended to create a series of notebooks that illustrate the FAIR principles in the context of High Energy Physics Data and AI models. The FAIR acronym stands for Findable, Accessible, Interoperable, and Reusable- benchmarking a set of desired qualities that ensure transparent and objective scientific data management.
- 01-Intro2FAIR.ipynb: Introduces the FAIR principles and a set metrics used to evaluate FAIRness of datasets
- 02-FAIRCheck-MNIST.ipynb: Explores the MNIST dataset and its FAIRness using the metrics introduced in the previous notebook
- 03-FAIRCheck-CDMS.ipynb: Explores the superCDMS dataset and its FAIRness
- 04-CDMS-LR.ipynb: Explores linear regression along with Ridge and Lasso Regularizations and preservation of these models
- 05-CDMS-PCA.ipynb: Explores Principal Component Analysis based linear regression