FY835: Information theory, inference, and learning algorithms
Study Board of Science
Teaching language: Danish, but English if international students are enrolled
EKA: N510046102, N510046112
Assessment: Second examiner: Internal, Second examiner: None
Grading: Pass/Fail
Offered in: Odense
Offered in: Spring
Level: Master
STADS ID (UVA): N510046101
ECTS value: 5
Date of Approval: 12-10-2022
Duration: 1 semester
Version: Archive
Entry requirements
Academic preconditions
Students taking the course are expected to: Have knowledge of probability theory, (f.ex. conditional probabilities).
Course introduction
NOTE that the teaching method in the course is special – see the elaboration on the teaching method below.
The aim of the course is to give the students knowledge of the Bayesian way of thinking and solving inference problems, as well as the thoughts behind information theory (Bayesian inference is a method where regular probability theory is extended to apply to hypothesis, whereby it constitutes an alternative to frequentist statistics. Information theory is about efficient storage and communication of data).
The course gives a foundation for applying Bayesian methods to analyse data, as for instance obtained through experiments, simulations or registration. This can for instance be used in projects in the rest of the education. The course also gives knowledge of the connection between information theory and the concept of entropy in statistical physics.
In relation to the competence profile of the degree it is the explicit focus of the course to:
- research-based knowledge of the basic theory formations and experimental methods of physics.
- describe, formulate and communicate issues and results to peers as well as non-specialists, partners and users.
Expected learning outcome
The learning objective of the course is that the student demonstrates the ability to:
- Autonomously acquire the knowledge about Bayesian inference and information theory as described under Contents
- Solve problems regarding fitting of parameters and model selection
- Present theory and exercises
- Apply the acquired knowledge within a chosen subject (final project)
Content
The following main topics are contained in the course:
- Interpretation of probability
- Model selection
- Fitting of parameters
- Bayes’ theorem
- Shannon entropy
- Coding theory
Literature
Examination regulations
Exam element a)
Timing
June
Prerequisites
Type | Prerequisite name | Prerequisite course |
---|---|---|
Examination part | Prerequisites for participating in the exam a) | N510046101, FY835: Information theory, inference, and learning algorithms |
Tests
Oral exam
EKA
N510046102
Assessment
Second examiner: Internal
Grading
Pass/Fail
Identification
Full name and SDU username
Language
Normally, the same as teaching language
Examination aids
To be announced during the course
ECTS value
5
Additional information
The exam takes its starting point in a written report about the final project. It takes the form of a presentation followed by questions.
Prerequisites for participating in the exam a)
Timing
Spring
Tests
Active participation in the teaching
EKA
N510046112
Assessment
Second examiner: None
Grading
Pass/Fail
Identification
Full name and SDU username
Language
Normally, the same as teaching language
Examination aids
To be announced during the course
ECTS value
0
Additional information
The prerequisite examination is a prerequisite for participation in exam element a).
First and foremost a number of presentations around the level of the total number divided by the number of students as well as posing questions during other students’ presentations. Besides that, some hand-ins.
First and foremost a number of presentations around the level of the total number divided by the number of students as well as posing questions during other students’ presentations. Besides that, some hand-ins.
Indicative number of lessons
Teaching Method
At the faculty of science, teaching is organized after the three-phase model ie. intro, training and study phase.
- Intro phase (lectures, class lessons): 16 hours
- Training phase: 15 hours including 15 hours of tutorials
The teaching method in the course is built around the students presenting the material for each other. At every class (2 hours) there will be typically 5-6 students who each spend approximately 10-15 min. on presenting a section or exercise from the textbook. The teachers will be available in between the classes if the presenters have questions to their material or exercise. Due to the additional time needed for preparing the presentations, the number of classes is lower than usual.
Activities during the study phase:
- Study of the textbook
- Solving of exercises
- Preparation of presentations
- Undertaking of project
Teacher responsible
Timetable
Administrative Unit
Team at Educational Law & Registration
Offered in
Recommended course of study
Transition rules
Transitional arrangements describe how a course replaces another course when changes are made to the course of study.
If a transitional arrangement has been made for a course, it will be stated in the list.
See transitional arrangements for all courses at the Faculty of Science.