DM873: Deep Learning

The Study Board for Science

Teaching language: Danish or English depending on the teacher, but English if international students are enrolled
EKA: N340031102
Assessment: Second examiner: External
Grading: 7-point grading scale
Offered in: Odense
Offered in: Autumn
Level: Master

STADS ID (UVA): N340031101
ECTS value: 10

Date of Approval: 07-04-2025


Duration: 1 semester

Version: Approved - active

Comment

The course is an elective for students in the following programme: Computer Science, Mathematics, Applied Math, Computational BioMedicine.
The course is co-read with DS809: Deep Learning 

Entry requirements

The course cannot be chosen by students who have taken DS809: Deep Learning (5 ECTS), DM568: Deep Learning (summer school) (5 ECTS), AI506 or DS833.

Academic preconditions

Students taking the course are expected to:

  • Have competences in programming in Python
  • Basic understanding of linear algebra

The course builds partly on the knowledge acquired in the course DM555 but can be taken by any Computer Science or Computational BioMedicine Master student.

Course introduction

Machine learning has become a part in our everydays life, from simple product recommendations to personal electronic assistant to self-driving cars. More recently, through the advent of potent hardware and cheap computational power, “Deep Learning” has become a popular and powerful tool for learning from complex, large-scale data.
In this course, we will discuss the fundamentals of deep learning and its application to various different fields. We will learn about the power but also the limitations of these deep neural networks. At the end of the course, the students will have significant familiarity with the subject and will be able to apply the learned techniques to a broad range of different fields.

Expected learning outcome

The learning objectives of the course is that the student demonstrates the ability to:
  • Describe the principles of deep neural networks in a scientific and precise language and notation
  • Analyze the various types of neural networks, the different layers and their interplay 
  • Describe the feasibility of deep learning approaches to concrete problems
  • Understand the theoretical mathematical foundations of the field 
  • Apply deep learning frameworks for solving concrete problems

Content

The following main topics are contained in the course:
  • feedforward neural networks
  • recurrent neural networks
  • convolutional neural networks
  • backpropagation algorithm
  • regularization
  • factor analysis
  • autoencoders

Literature

See itslearning for syllabus lists and additional literature references.

Examination regulations

Exam element a)

Timing

Autumn and January

Tests

Portfolio

EKA

N340031102

Assessment

Second examiner: External

Grading

7-point grading scale

Identification

Full name and SDU username

Language

Normally, the same as teaching language

Duration

Oral exam - 15 minutes

Examination aids

1 page of notes + slides/presentation aids allowed 

ECTS value

10

Additional information

Portfolio exam consisting of two parts:
  1. Two mandatory assignments handed in during the course
  2. Oral examination
The oral exam consists of a 5 min presentation of a randomly selected thematic topic (selected during the exam) from a preannounced list of thematic topics.The presentation is followed by questions/answers to potentially all topics of the course, including the assign-ments.

To achieve a passing grade overall, both elements 1 and 2 must individually meet the learning objectives.
The assessment of element 1 takes place in conjunction with the completion of element 2. The grade is primarily based on element 2, but element 1 can raise or lower the grade by one grade step.

Indicative number of lessons

48 hours per semester

Teaching Method

Planned lessons: 

Total number of planned lessons: 48 

Hereof: 

Common lessons in classroom/auditorium: 48 

The course will consist of frontal lectures supported by discussion sessions. The students will get accompanying exercises demonstrating the collected knowledge on practical real-world problems. The student activation is completed by a mandatory project and discussions of current state-of-the-art research papers

Other planned teaching activities: 

  • Small take home exercises
  • Study latest developments and approaches of deep learning by reading recent publications

Teacher responsible

Name E-mail Department
Richard Röttger roettger@imada.sdu.dk Data Science

Timetable

Administrative Unit

Institut for Matematik og Datalogi (datalogi)

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.