USCMS Researcher: Ruchi Chudasama
Postdoc dates: Sep 2022 - Sep 2023
Home Institution: The University of Alabama
Project: Accelerating Machine Learning Reconstruction in CMS
Development of end-to-end deep learning algorithms to improve the electron and tau identification in low momentum regime using graph neural networks and vision transformers. Integrate the electron and tau benchmarks into CMS software framework and scaling studies of deep learning training and inference on heterogeneous hardware platforms relying on containerization. Additionally, extend the end-to-end deep learning for electron and tau mass regression.More information: My project proposal
Mentors:
-
Sergei Gleyzer (The University of Alabama)
- 9 May 2023 - "End-to-end deep learning inference with CMSSW via ONNX using Docker ", Ruchi Chudasama, 26th International Conference on Computing in High-Energy and Nuclear Physics
Current Status
Contact me: