The Thesis Review [21] Michela Paganini - Machine Learning Solutions for High Energy Physics
Mar 19, 2021
Michela Paganini, a Research Scientist at DeepMind, focuses on compressing and scaling neural networks. She shares insights from her PhD on machine learning in high energy physics, particularly around the ATLAS experiment at CERN. The conversation delves into jet tagging and the evolution from traditional methods to deep learning. Michela reflects on her transformative experiences at CERN during the Higgs boson discovery and the interplay between physics and machine learning, emphasizing mentorship's role in her innovative journey.
AI Snips
Chapters
Transcript
Episode notes
Physics vs. ML Understanding
- Both understanding fundamental particles and deep neural networks are extremely difficult problems with no absolute notion of completeness.
- Physics understanding is more mature, while machine learning still has much growth ahead as a field.
ML Engineering vs Physics Science
- Machine learning is currently more engineering and task-driven, while physics pursues deep understanding of fundamental interactions.
- The ML community lacks unified consensus on understanding models compared to physics.
CERN Higgs Discovery Internship
- Michela interned at CERN during the Higgs discovery announcement, working on antimatter production with the University of Milan team.
- Being at CERN and witnessing that moment was a decisive and impactful experience for her career path.