NWI-NM116B
Machine Learning in Particle Physics and Astronomy
Course infoSchedule
Course moduleNWI-NM116B
Credits (ECTS)6
CategoryMA (Master)
Language of instructionEnglish
Offered byRadboud University; Faculty of Science; Wiskunde, Natuur- en Sterrenkunde;
Lecturer(s)
Coordinator
dr. S. Caron
Other course modules lecturer
Examiner
dr. S. Caron
Other course modules lecturer
Contactperson for the course
dr. S. Caron
Other course modules lecturer
Lecturer
dr. S. Caron
Other course modules lecturer
Lecturer
dr. B.P.J. Stienen
Other course modules lecturer
Academic year2021
Starting block
JAAR/  KW3
Course mode
full-time
Remarks-
Registration using OSIRISYes
Course open to students from other facultiesYes
Pre-registrationNo
Waiting listNo
Placement procedure-
Aims
  • The student can apply basic statistical data analysis concepts (e.g. probabilities, likelihoods, confidence level, frequentist, bayesian statistics)
  • The student understands and can apply basic Machine Learning methods (simple regression, test statistics, training etc.)
  • The student can solve classification and regression problems with Machine Learning methods and explain how these methods work
  • The student can explain basic concepts of image analysis and is able to apply image analysis algorithms (convolutional networks)
  • The student can analyse sequential (temporal) data with the help of recurrent networks
  • The student can explain the concepts of generative networks and optimization algorithms and can practically apply such algorithms
Content

This lecture discusses recent developments in Data Science and Machine Learning used in the fields of Particle Physics and Astronomy.
Various practical examples are explained and hands-on exercises are used to learn the material.
We will use the python programming language. Basic knowledge of python is required. 

The course covers the following topics:
- Introduction into statistical data analysis (e.g. probabilities, likelihoods, confidence level, frequentist, bayesian statistics)
- Introduction into basic Machine Learning methods (simple regression, test statistics, training etc.)
- Finding signal events in background events (classification and decision trees)
- Learning a Function (regression and deep networks)
- Image Analysis in Particle Physics and Astronomy (Computer Vision)
- Radio and gravitational wave analysis (Signal Detection in temporal data, recurrent networks)
- Generating Data (Generative Networks)
- Fitting Data (Optimalization and Sampling Algorithms)
 
Level

Presumed foreknowledge
Working knowledge of python programming language.
Test information
The exam will be in the form of a programming exercise.
Specifics

Recommended materials
In consultation with teacher
Lecture notes will be made available
Sheets
will be made available

Instructional modes
Course
Attendance MandatoryYes

Lecture

Tutorial
Attendance MandatoryYes

Zelfstudie

Tests
Programming Excercise
Test weight1
Test typeAssignment
OpportunitiesBlock JAAR