Machine Learning

Machine Learning for Fundamental Physics

Vision: To advance the potential for discovery and interdisciplinary collaboration by approaching fundamental physics challenges through the lens of modern machine learning.

Mission: The Physics Division Machine Learning group is a cross-cutting effort that connects researchers developing, adapting, and deploying artificial intelligence (AI) and machine learning (ML) solutions to fundamental physics challenges across the HEP frontiers, including theory. While most of the ML group members will have a primary affiliation with other areas of the division, there will be unique efforts within the group to develop methods with significant interdisciplinary potential. We have strong connections and collaborations with researchers in the Scientific Data Division, the National Energy Research Scientific Computing Center (NERSC), and the Berkeley Institute of Data Science (BIDS).

A variety of cross-cutting themes form the core of our research program:

  1. Anomaly Detection
  2. Likelihood-free Inference
  3. Generative Models and Simulation
  4. Pattern Recognition, Calibration and Noise Mitigation
  5. Label-free learning / Simulation Agnostic Approaches
  6. Physics-aware Learning
  7. Uncertainty Quantification and Interpretability
  8. Hardware Interface