FY835: Information theory, inference, and learning algorithms

The Study Board for Science

Teaching language: Danish, but English if international students are enrolled
EKA: N510046102
Assessment: Second examiner: None
Grading: Pass/Fail
Offered in: Odense
Offered in: Spring
Level: Master

STADS ID (UVA): N510046101
ECTS value: 5

Date of Approval: 11-11-2024


Duration: 1 semester

Version: Approved - active

Entry requirements

None

Academic preconditions

Students taking the course are expected to: Have knowledge of probability theory.

Course introduction

The course aims to give the student an introduction to information theory in particular, but also Bayesian inference and neural networks, and to show how these topics are different sides of the same coin.

Information theory plays a major role in statistical physics, as the mathematical theory of entropy, and inference and machine learning are central to for instance analysis of experimental data. The course can therefore be applied in projects during the rest of the education.

In relation to the competence profile of the degree the explicit focus of the course is on:
  • research-based knowledge of the basic theory formations and experimental methods of physics.
  • describing, formulating and communicating 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 information theory, inference and machine learning as described under Contents
  • Apply this knowledge in solving 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 and parameter fitting
  • Shannon entropy
  • Data compression
  • Communication over noisy channels
  • Monte Carlo methods
  • Neural networks

Literature

See itslearning for syllabus lists and additional literature references.

Examination regulations

Exam element a)

Timing

Spring and June

Tests

Portfolio exam

EKA

N510046102

Assessment

Second examiner: None

Grading

Pass/Fail

Identification

Full name and SDU username

Language

Normally, the same as teaching language

Duration

Oral exam - 15 minutes

Examination aids

To be announced during the course 

ECTS value

5

Additional information

Portfolio consisting of:
1) Active participation in the teaching, i.e., participants must contribute to the lessons with teaching components, for instance give a small presentation about a topic or exercise, come up with a multiple choice question, or lead a reflection discussion. Alternatively, for instance if one cannot participate on a certain day, then showing a solved exercise in that day's topic can count as active participation.
2) Written report
3) Oral exam. The exam is based on a written report about a final project, and takes the form of an approximately 15 minute presentation with subsequent questions.

All three elements must be present in order to obtain a passing grade.

Indicative number of lessons

31 hours per semester

Teaching Method

The teaching is structured around a series of video lectures that can be supplemented with study of the textbook. The teaching in the classes is driven by the students, and includes reflections over and discussions of the video lectures, possibly supplemented with presentations of additional material from the textbook. Besides this, exercises from the textbook will be solved in the classes.

At the end of the course a small final project is chosen that applies the acquired knowledge.

The course will contain a one hour introductory meeting followed by 14 two-hour classes. For each of these classes there will be video lectures that need to be watched prior to the class. They are of varying length around 1 to 1.5 hours.

Teacher responsible

Name E-mail Department
Michael Lomholt mlomholt@sdu.dk Fysik

Timetable

Administrative Unit

Fysik, kemi og Farmaci

Team at Registration

NAT

Offered in

Odense

Recommended course of study

Profile Education Semester Offer period

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.