Between Models and Reality: School on Machine Learning in Physics

Europe/Copenhagen
Auditorium A (Niels Bohr Institute)

Auditorium A

Niels Bohr Institute

Blegdamsvej 17, 2100 Copenhagen
Troels Petersen (Niels Bohr Institute)
Description

Welcome to the "Between Models and Reality" Ph.D. school on Machine Learning in physics. The focus of this school is the application of Machine Learning to physics research and the many challenges and solutions that this entails. The focus is mainly on application, and will not only consist of lectures.

So if you are a Ph.D. student in a field of physics (or a related "large research data" science), who would like to learn more about both basic but also more advanced Machine Learning approaches and ways of thinking, don't hesitate to apply.

The School is held in collaboration between the 4EU+ alliance of universities (Prague, Heidelberg, Paris (Panthéon-Assas and Sorbonne), Copenhagen, Geneva, Milan, Warsaw) and the AI-Physics Marie Curie Ph.D. network, but is open to all.

The school will be held in the famous Auditorium A at the Niels Bohr Institute in central Copenhagen. There is room for 60 students, which will be accepted on a first-come-first-serve basis, provided that the students fulfills the requirements and submits a well motivated registration.

Lectures will be run by a diverse group of physicists and computer scientists, including the world-class researchers Tilman Plehn (Univerity of Heidelberg) and Thea Aarrestad (ETH Zurich), who along with experts on specialised subjects will lecture on topics such as:

  • Bayesian neural networks
  • Uncertainty quantification & learning
  • Generative machine learning
  • Representation learning
  • Fast machine learning
  • Physics-informed neural networks

 

The course is free of charge for students from the 4EU+ alliance (Prague, Heidelberg, Paris (Panthéon-Assas and Sorbonne), Copenhagen, Geneva, Milan, Warsaw), AIPHY and for PhD students enrolled at universities that are part of the Danish open market for PhD courses. For students from other universities there is a fee of 3.000 DKK (400 Euro) covering tuition, catering during the course, and social events. Students must arrange for travel and accommodation themselves.

 

Essential Links:

ML links: https://www.nbi.dk/~petersen/Teaching/ML2025/MLlinks.html

GitHub for school exercises: https://github.com/troelspetersen/PhDschool2025_AppML

Link to “Kaggle Challenge” setup/rules: https://www.nbi.dk/~petersen/PhDschool2025/PhDschool2025_InitialProject.html

Google link for submitting “Kaggle Challenge” solutions: https://docs.google.com/forms/d/1_IHeU9aBWtbQQza1c9thweWhc47qcZZBWxU-fKd0V9s/edit

Deadline is Thursday at noon - we will then start to evaluate the solutions.

The “School Proximity” MeetUp App: https://hamlet-conf.github.io/nbi-school-25/

Evaluation of school: https://docs.google.com/forms/d/1FAXt0fLVCAEozMwX3K8ef_ihCSn_WkLl2wIjYSRS5h0/edit

 

Contact / Organiser
    • 1
      Arrival, Breakfast, Registration Auditorium A

      Auditorium A

      Niels Bohr Institute

      Blegdamsvej 17, 2100 Copenhagen
      Speaker: Troels Petersen (Niels Bohr Institute)
    • 2
      Scope of School and Lecture 1: Introduction and overview of Machine Learning Auditorium A

      Auditorium A

      Niels Bohr Institute

      Blegdamsvej 17, 2100 Copenhagen
      Speaker: Troels Petersen (Niels Bohr Institute)
    • 10:45
      Break Auditorium A

      Auditorium A

      Niels Bohr Institute

      Blegdamsvej 17, 2100 Copenhagen
    • 3
      Lecture 2: Basics of Machine Learning & Fast Data Loaders Auditorium A

      Auditorium A

      Niels Bohr Institute

      Blegdamsvej 17, 2100 Copenhagen
      Speakers: Inar Timiryasov (NBI), Troels Petersen (Niels Bohr Institute)
    • 12:15
      Lunch Canteen

      Canteen

      Niels Bohr Institute

      Blegdamsvej 17, 2100 Copenhagen, Denmark
    • 4
      Discussion of Lectures and Introduction to exercises K-building, floor E (top floor)

      K-building, floor E (top floor)

      Niels Bohr Institute

      Speaker: Daniel Murnane (Niels Bohr Institute, University of Copenhagen)
    • 5
      Work on exercises K-building, floor E (top floor)

      K-building, floor E (top floor)

      Niels Bohr Institute

      Speakers: Daniel Murnane (Niels Bohr Institute, University of Copenhagen), Rasmus Ørsøe (TUM), Troels Petersen (Niels Bohr Institute)
    • 14:30
      Break Auditorium A

      Auditorium A

      Niels Bohr Institute

      Blegdamsvej 17, 2100 Copenhagen
    • 6
      Work on exercises K-building, floor E (top floor)

      K-building, floor E (top floor)

      Niels Bohr Institute

      Speakers: Daniel Murnane (Niels Bohr Institute, University of Copenhagen), Rasmus Ørsøe (TUM), Troels Petersen (Niels Bohr Institute)
    • 08:30
      Breakfast Auditorium A

      Auditorium A

      Niels Bohr Institute

      Blegdamsvej 17, 2100 Copenhagen
    • 7
      Lecture 3: Networks with Learned Uncertainties Auditorium A

      Auditorium A

      Niels Bohr Institute

      Blegdamsvej 17, 2100 Copenhagen

      All my lectures will be on the blackboard, based on the published Heidelberg lecture notes. Tutorials maintained by the Heidelberg group are linked in the lecture notes.

      Speaker: Tilman Plehn (Heidelberg University)
    • 10:15
      Break Auditorium A

      Auditorium A

      Niels Bohr Institute

      Blegdamsvej 17, 2100 Copenhagen
    • 8
      Lecture 4: Generative Networks and Classifier Tests Auditorium A

      Auditorium A

      Niels Bohr Institute

      Blegdamsvej 17, 2100 Copenhagen
      Speaker: Tilman Plehn (Heidelberg University)
    • 12:00
      Lunch Auditorium A

      Auditorium A

      Niels Bohr Institute

      Blegdamsvej 17, 2100 Copenhagen
    • 9
      Discussion of Lectures and intro to exercises Auditorium A

      Auditorium A

      Niels Bohr Institute

      Blegdamsvej 17, 2100 Copenhagen
    • 10
      Work on exercises Auditorium A

      Auditorium A

      Niels Bohr Institute

      Blegdamsvej 17, 2100 Copenhagen
    • 14:30
      Break & School Photo Auditorium A

      Auditorium A

      Niels Bohr Institute

      Blegdamsvej 17, 2100 Copenhagen
    • 11
      Work on exercises Auditorium A

      Auditorium A

      Niels Bohr Institute

      Blegdamsvej 17, 2100 Copenhagen
    • 08:30
      Breakfast Auditorium A

      Auditorium A

      Niels Bohr Institute

      Blegdamsvej 17, 2100 Copenhagen
    • 12
      Lecture 5: Modern Generative Networks Auditorium A

      Auditorium A

      Niels Bohr Institute

      Blegdamsvej 17, 2100 Copenhagen
      Speaker: Tilman Plehn (Heidelberg University)
    • 10:15
      Break Auditorium A

      Auditorium A

      Niels Bohr Institute

      Blegdamsvej 17, 2100 Copenhagen
    • 13
      Lecture 6: Probabilistic regression with generative models Auditorium A

      Auditorium A

      Niels Bohr Institute

      Blegdamsvej 17, 2100 Copenhagen
      Speaker: Malte Algren
    • 12:00
      Lunch break Auditorium A

      Auditorium A

      Niels Bohr Institute

      Blegdamsvej 17, 2100 Copenhagen
    • 14
      Discussion of Lectures and intro to exercises Auditorium A

      Auditorium A

      Niels Bohr Institute

      Blegdamsvej 17, 2100 Copenhagen
    • 15
      Work on exercises Auditorium A

      Auditorium A

      Niels Bohr Institute

      Blegdamsvej 17, 2100 Copenhagen
    • 14:30
      Packing up, walking to Østerport train station, and preparing for boarding train. Auditorium A

      Auditorium A

      Niels Bohr Institute

      Blegdamsvej 17, 2100 Copenhagen
    • 16
      Train ride to Helsingør, visit to Kronborg Castle, drinks on the ramparts, and dinner at Værftets Madmarket. Auditorium A

      Auditorium A

      Niels Bohr Institute

      Blegdamsvej 17, 2100 Copenhagen
    • 08:30
      Breakfast Auditorium A

      Auditorium A

      Niels Bohr Institute

      Blegdamsvej 17, 2100 Copenhagen
    • 17
      Lecture 7: Anomaly Detection Auditorium A

      Auditorium A

      Niels Bohr Institute

      Blegdamsvej 17, 2100 Copenhagen
      Speaker: Thea Aarrestad (ETH Zurich)
    • 10:15
      Break Auditorium A

      Auditorium A

      Niels Bohr Institute

      Blegdamsvej 17, 2100 Copenhagen
    • 18
      Lecture 8: Network optimisation and fast inference Auditorium A

      Auditorium A

      Niels Bohr Institute

      Blegdamsvej 17, 2100 Copenhagen
      Speaker: Thea Aarrestad (ETH Zurich)
    • 12:00
      Lunch Break Auditorium A

      Auditorium A

      Niels Bohr Institute

      Blegdamsvej 17, 2100 Copenhagen
    • 19
      Work on exercises and own projects Auditorium A

      Auditorium A

      Niels Bohr Institute

      Blegdamsvej 17, 2100 Copenhagen
    • 14:30
      Break Auditorium A

      Auditorium A

      Niels Bohr Institute

      Blegdamsvej 17, 2100 Copenhagen
    • 20
      Work on exercises and own projects Auditorium A

      Auditorium A

      Niels Bohr Institute

      Blegdamsvej 17, 2100 Copenhagen
    • 08:30
      Breakfast Auditorium A

      Auditorium A

      Niels Bohr Institute

      Blegdamsvej 17, 2100 Copenhagen
    • 21
      Lecture 9: Transformers and Foundation Models Auditorium A

      Auditorium A

      Niels Bohr Institute

      Blegdamsvej 17, 2100 Copenhagen
      Speaker: Malte Algren
    • 10:15
      Break Auditorium A

      Auditorium A

      Niels Bohr Institute

      Blegdamsvej 17, 2100 Copenhagen
    • 22
      Lecture 10: Domain shifts and Past experiences Auditorium A

      Auditorium A

      Niels Bohr Institute

      Blegdamsvej 17, 2100 Copenhagen
      Speaker: Troels Petersen (Niels Bohr Institute)
    • 12:00
      Lunch Break Auditorium A

      Auditorium A

      Niels Bohr Institute

      Blegdamsvej 17, 2100 Copenhagen
    • 23
      Discussion of Lectures Auditorium A

      Auditorium A

      Niels Bohr Institute

      Blegdamsvej 17, 2100 Copenhagen
    • 24
      Exchange of experiences, resources, and "tricks" Auditorium A

      Auditorium A

      Niels Bohr Institute

      Blegdamsvej 17, 2100 Copenhagen
    • 25
      Presentation of projects over drinks and snacks Auditorium A

      Auditorium A

      Niels Bohr Institute

      Blegdamsvej 17, 2100 Copenhagen