NDAK15014U Advanced Topics in Machine Learning (ATML)

Volume 2019/2020

MSc Programme in Computer Science

MSc Programme in Statistics


The purpose of this course is to expose students to selected advanced topics in machine learning. The course will bring the students up to a level sufficient for writing a master thesis in machine learning.

The course is relevant for computer science students as well as students from other studies with good mathematical background, including Statistics, Actuarial Mathematics, Mathematics-Economics, Physics, etc.

The exact list of topics will depend on the lecturers and trends in machine learning research and will be announced on the course's Absalon page. Feel free to contact the course organiser for details.

Examples of topics that were taught in the last year include:

  • PAC-Bayesian analysis

    • The soul of Machine Learning: How to trade-off prior knowledge and data fit in a principled way

  • Optimization and Machine Learning

    • Mathematical tools for solving machine learning problems (gradient descent; the method of Lagrange multipliers; alternating minimization; etc.)

  • Online learning
    • How to learn when data collection and learning are coupled together

    • How to adapt to changing and adversarial environments

  • Reinforcement learning

    • How to learn when agent's actions are changing its state

Learning Outcome

Knowledge of

Selected advanced topics in machine learning, including:

  • design of learning algorithms
  • analysis of learning algorithms

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

Skills to

  • Read and understand recent scientific literature in the field of machine learning
  • Apply the knowledge obtained by reading scientific papers
  • Compare machine learning methods and assess their potentials and shortcomings

Competences to

  • Understand advanced methods, and apply the knowledge to practical problems
  • Plan and carry out self-learning

See Absalon.

The course requires strong mathematical background. It is suitable for computer science master students, as well as students from mathematics (statistics, actuarial math, math-economics, etc) and physics study programs. Students from other study programs can verify sufficiency of their math and programming skills by solving the self-preparation assignment (below) and if in doubt contact the course organizer.

It is assumed that the students have successfully passed the “Machine Learning” course offered by the Department of Computer Science (DIKU). In case you have not taken the “Machine Learning” course at DIKU, please, go through the self-preparation material and solve the self-preparation assignment provided at https:/​/​sites.google.com/​diku.edu/​machine-learning-courses/​atml before the course starts. (For students with strong mathematical background and some background in machine learning it should be possible to do the self-preparation within a couple of weeks.)

Academic qualifications equivalent to a BSc degree is recommended.
Lectures, class instructions and weekly home assignments.
  • Category
  • Hours
  • Class Instruction
  • 14
  • Exercises
  • 94
  • Lectures
  • 28
  • Preparation
  • 70
  • Total
  • 206
Continuous feedback during the course of the semester

The course is based on weekly home assignments, which are scored continuously during the course of the semester

7,5 ECTS
Type of assessment
Continuous assessment
5-7 weekly take home exercises.
The final grade will be the average over all assignments except the worst one.
All aids allowed
Marking scale
7-point grading scale
Censorship form
No external censorship
Several internal examiners

The re-exam consists of two parts. The two parts will be given an overall assessment.
The first part is handing in at least 5 of the course assignments no later than 2 weeks before the oral part of the exam.
The second part is an oral exam (30 minutes) in the course curriculum without preparation.

Criteria for exam assesment

See Learning Outcome.