Advanced Topics in Machine Learning (ATML)

Course content

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

The course is relevant for computer science students as well as students from others studies with good mathematical background, including Statistics, Mathematics, Mathematics-Economics, Physics,  Bioinformatics, …

Examples of topics that were taught in previous years include:

  • Classical generalization bounds
    • Why is it possible to make predictions about the future based on past observations
    • When is it possible, when is it impossible, and how much can we trust the predictions
  • Advanced topics on Support Vector Machines
    • Learn fast ways to train one of the most successful learning models – Support Vector Machines
  • PAC-Bayesian analysis
    • The soul of Machine Learning: How to trade-off model complexity, data complexity, and prior knowledge in a principled way
  • 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 our actions influence our state

 

** The exact list of topics in the current year will depend on the lecturers and trends in machine learning research and will be announced on the course Absalon website. Feel free to contact the course responsible for details.

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 website.

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 shortcommings
     

Competences to

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

Lectures and class instructions.

See Absalon.

Passed the course "Machine Learning" or "Statistical Methods for Machine Learning" or similar.
Good mathematical background.

ECTS
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.
Aid
All aids allowed
Marking scale
7-point grading scale
Censorship form
No external censorship
Several internal examiners
Criteria for exam assessment

To obtain the grade 12 the student must be able to:

1.    Document understanding of the assignments including the relevant literature and/or other materials needed for conducting the assignment.
2.    Document solutions to the assignment.
3.    Document any experiments made and any drawn conclusions.

 

Single subject courses (day)

  • Category
  • Hours
  • Lectures
  • 28
  • Class Instruction
  • 14
  • Preparation
  • 70
  • Exercises
  • 74
  • Exam Preparation
  • 20
  • English
  • 206