NDAB20002U Artificial Intelligence (AI)

Volume 2020/2021

BSc Programme in Machine Learning and Data Science


Introduction to models and methods used in artificial intelligence (AI), and machine learning methods relevant to AI. Different aspect of AI are covered including symbolic AI, representation learning, advanced deep models, and reinforcement learning.

Learning Outcome

Knowledge of

  • general aspects of AI, weak vs. strong AI

  • history of AI

  • aspects of symbolic AI (knowledge bases, logic, reasoning)

  • representation learning

  • advanced deep models (recurrent networks, graph networks)

  • variational Bayesian methods (variational autoencoders)

  • reinforcement learning


Skills to

  • select appropriate methodology to solve AI problems

  • implement selected AI algorithms

  • design and train representation learning algorithms

  • design and train reinforcement learning algorithms


Competences to

  • reflect upon the capabilities and limitations of AI algorithms

  • recognising and describing possible applications of AI methodology

  • design, optimise and use advanced deep models

  • apply the learned methodology to applications in analysis of real-world data such as images, sounds and text

  • rigorously analyse AI learning algorithms

See Absalon for course litterature.

Academic qualifications corresponding to the previous courses on the BSc in Machine learning & data science. As a minimum this implies:

1. Linear algebra corresponding to the course Lineær Algebra i datalogi (LinAlgDat).
2. Calculus corresponding to the courses Introduktion til matematik i naturvidenskab (MatIntroNat) and Matematisk Analyse (MatAn).
3. Basic statistics and probability theory corresponding to the course Sandsynlighedsregning og statistik (SS), and statistical modelling corresponding to the course Modeller for Komplekse Systemer (ModKomp).
4. Machine learning corresponding to Introduktion til Machine Learning (MaLeIntro). Please note that MaLeIntro includes basic deep learning.
5. Programming experience in Python.
The course will mix lectures, exercise classes, and project work.
  • Category
  • Hours
  • Lectures
  • 32
  • Preparation
  • 68
  • Exercises
  • 46
  • Exam
  • 60
  • Total
  • 206
Continuous feedback during the course of the semester
7,5 ECTS
Type of assessment
Continuous assessment
Continuous assessment of 4 written assignments (2 to be completed individually, and 2 to be completed in groups). All assignments must be passed. The final grade is based on an overall assessment.
All aids allowed
Marking scale
7-point grading scale
Censorship form
No external censorship
Several internal examiners

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

Criteria for exam assesment

According to learning outcomes.