NDAK24003U Advanced Topics in Deep Learning (ATDL)

Volume 2024/2025

MSc Programme in Computer Science


This course will give you detailed insight into advanced deep learning methods and techniques, covering algorithms, theory and tools in this exciting and fast advancing field.

This is an advanced topics course, and the exact list of topics will therefore change from year to year, depending on current trends in the literature.

The course is on advanced topics, and it therefore has the introductory machine learning and deep learning courses as prerequisites.

Learning Outcome

Knowledge of

Selected advanced topics in deep learning, including:

  • state-or-the-art deep models in selected domains

  • design of deep learning algorithms

  • analysis of deep learning algorithms

  • theory of deep learning

The exact list of topics will depend on the teachers and trends in deep learning research. They will be announced on the course's Absalon page.

Skills to

  • Implement selected advanced deep learning algorithms using state-of-the-art tools

  • Read and understand recent scientific literature in the field of deep learning

  • Apply the knowledge obtained by reading scientific papers

  • Compare deep learning methods and assess their potentials and shortcomings

Competences to

  • Understand advanced deep learning methods and techniques

  • Design, optimize and use advanced deep models

  • Plan and carry out self-learning

See Absalon.

Academic qualifications equivalent to a BSc degree and the following courses are recommended:

- Machine learning corresponding to the courses Machine Learning A (MLA) and Deep learning (DL).
- Solid programming experience in Python.
- Linear algebra corresponding to the course Linear Algebra in Computer Science (LinAlgDat).
- Calculus corresponding to the courses Mathematical Analysis and Probability Theory for Computer Scientists (MASD) and Modelling and Analysis of Data (MAD), or Introduction to Mathematics for Science (MatIntroNat) and Mathematical Analysis (MatAn), or equivalent.
- Statistics and probability theory corresponding to the course Probability Theory and Statistics (SS).
The course will mix lectures, exercise classes, and project work.
  • Category
  • Hours
  • Lectures
  • 28
  • Class Instruction
  • 14
  • Preparation
  • 70
  • Exercises
  • 94
  • Total
  • 206
Continuous feedback during the course of the semester
Peer feedback (Students give each other feedback)
7,5 ECTS
Type of assessment
Continuous assessment
Type of assessment details
Continuous assessment of 3-4 written assignments. All assignments must be passed. The final grade is based on an overall assessment.
All aids allowed

For programming tasks specifically, this includes AI-based programming tools such as github copilot or similar.

Marking scale
7-point grading scale
Censorship form
No external censorship
Internal examiner.

The re-exam is 25 minutes oral examination, without preparation, in full course syllabus.

Criteria for exam assesment

See Learning outcome