NDAK15014U Advanced Topics in Machine Learning (ATML)

Volume 2020/2021
Education

MSc Programme in Statistics

Content

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 a 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

WARNING: If you have not taken DIKU's Machine Learning master course, please, carefully check the "Recommended Academic Qualifications" box below and the self-preparation assignment at https:/​/​sites.google.com/​diku.edu/​machine-learning-courses/​atml. Machine Learning courses given at other places do not necessarily prepare you well for this course. It is not advised taking the course if you do not meet the academic qualifications.

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 a 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 programmes. Students from other study programmes can verify if they have sufficient math and programming skills by solving the self-preparation assignment (below) and if in doubt contact the course organiser.

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 a strong mathematical background and some background in machine learning it should be possible to do the self-preparation within a couple of weeks.) It is strongly not advised taking the course if you do not meet the prerequisites.
Lectures, class instructions and weekly home assignments.
  • Category
  • Hours
  • Lectures
  • 28
  • Class Instruction
  • 14
  • Preparation
  • 70
  • Exercises
  • 94
  • Total
  • 206
Written
Continuous feedback during the course of the semester
Credit
7,5 ECTS
Type of assessment
Continuous assessment
5-7 weekly take-home assignments. The assignments must be solved individually.

The course is based on weekly home assignments, which are graded continuously over the course of the semester. The final grade is given as a weighted average of the assignments, except the assignment with the poorest assessment.
Aid
All aids allowed
Marking scale
7-point grading scale
Censorship form
No external censorship
Several internal examiners
Re-exam

The re-exam consists of two parts:

1. The first part is handing in at least 5 of the course assignments no later than 2 weeks before the oral part of the re-exam
2. The second part is a 30 minutes oral examination without preparation in the course curriculum

The final grade will be given as an overall assessment of the two re-exam parts.

Criteria for exam assesment

See Learning Outcome.