IRIS-HEP Fellow: Bornik Nag



Fellowship dates: Jun – Aug, 2026

Home Institution: Purdue University


Project: Towards Interpretable Machine Learning in High-Energy Physics - Development of an Explainability Framework

Survey interpretability techniques for ML models used in HEP, and propose practical guidelines for the field. The main deliverable will be twofold — firstly a practical set of guidelines: when should HEP physicists use which interpretability approach, what are the pitfalls, and where are the open problems? Secondly: an open source repository of tools that can be used to understand ML models.



More information: My project proposal

Mentors:

  • Liv Våge (Princeton University)

Presentations and Publications
Current Status


Contact me: