Machine Learning for Physics and Astronomy

6 EC

Semester 2, period 5

5354MLFP6Y

Owner Master Physics and Astronomy (joint degree)
Coordinator dr. C. Weniger
Part of Master Physics and Astronomy, track Advanced Matter and Energy Physics, Master Physics and Astronomy, track Science for Energy and Sustainability, Master Physics and Astronomy, track Theoretical Physics, Master Physics and Astronomy, track GRAPPA, Master Physics and Astronomy, track Astronomy and Astrophysics, Master Physics and Astronomy (joint degree), track Biophysics and Biophotonics, Master Physics and Astronomy (joint degree), track General Physics and Astronomy,

Course manual 2023/2024

Course content

Machine learning refers to a wide range of techniques that enable machines to learn from data, both with the aim to classify data or making predictions for future observations or outcomes. Since predictions are always uncertain, machine learning and statistics are closely related fields. In the context of physics and astronomy, we are in a special situation since we often have precise principled predictions based on physical models, which we want to compare with data. 

In this course, we will start with a crash course in statistics, and discuss some classical machine learning techniques. Those classical techniques form the backbone of modern developments in machine learning like deep neural networks and deep learning.  After discussing the basics of deep learning, we will finally conclude with recent developments in simulator-based inference, transformer and diffusion models.

Study materials

Other

  • See canvas page for details.

Objectives

  • Understand and apply probability calculus.
  • Apply Bayesian and Frequentist decision making techniques.
  • Application of standard ML techniques (e.g. linear regression, logistic regression, kernel estimation, clustering, PCA).
  • Theory and application of neural networks (classification/regression, generative models, likelihood-free inference).
  • Create and optimize neural network structures for toy learning problems.

Teaching methods

  • Lecture
  • Self-study
  • Working independently on e.g. a project or thesis
  • Laptop seminar

Learning activities

Activity

Hours

Hoorcollege

28

Laptopcollege

28

Tentamen

3

Self study

109

Total

168

(6 EC x 28 uur)

Attendance

Requirements concerning attendance (OER-B).

  • In addition to, or instead of, classes in the form of lectures, the elements of the master’s examination programme often include a practical component as defined in article A-1.2 of part A. The course catalogue contains information on the types of classes in each part of the programme. Attendance during practical components is mandatory.

    • Additional requirements for this course:

    Attendance of lectures and TA sessions is mandatory. Absence needs to be communicated to the course coordinator.

    Assessment

    Item and weight Details

    Final grade

    0.8 (80%)

    Tentamen

    0.1 (10%)

    Mini-project

    0.05 (5%)

    Self-evaluation test exam

    0.05 (5%)

    Active reading

    The final grade is based on the exam (80%), a mini-project (10%), active reading (5%) and a self-evaluation test exam (5%). Obtaining 50% of the problem set grades is required to be admitted to the exam.

    Fraud and plagiarism

    The 'Regulations governing fraud and plagiarism for UvA students' applies to this course. This will be monitored carefully. Upon suspicion of fraud or plagiarism the Examinations Board of the programme will be informed. For the 'Regulations governing fraud and plagiarism for UvA students' see: www.student.uva.nl

    Course structure

    WeeknummerOnderwerpenStudiestof
    1
    2
    3
    4
    5
    6
    7
    8

    Contact information

    Coordinator

    • dr. C. Weniger