Introduction to Machine Learning





Offered by

ICT Engineering




The course requires mathematics corresponding to the admission requirements for the ICT Engineering Programme. Knowledge about statistical and probability theory similar to that offered in the course Stochastic Modelling and Processes is recommended. It is also recommended taking the elective course in Applied Linear Algebra simultaneously.

Main purpose

Through the course the students attain knowledge and practical experience applying machine learning meth-ods and tools to both structured and unstructured data problems. The students will attain in depth knowledge about tools and techniques, will be able to prepare data (through preprocessing) and use them to determine underlying structures as well as make predictions. The course evolves around the following four main topics:
• Supervised learning
• Unsupervised learning
• Voice recognition
• Neural Networks


After having successfully completed the course, the student will have gained knowledge about theories, methods, techniques, tools, and applications within the following fundamental machine learning methods:
  • predictive methods, e.g. regression and classification
  • descriptive methods, e.g. clustering and factor analysis
  • deep learning methods, e.g. neural networks.
The students must be able to relate critically and reflectively to the above topics; In particular, it is important that they become proficient in selecting the right type of machine learning method for use in a given context.


After having successfully completed the course, the students should be able to apply the theories, methods and models from the above-mentioned areas to identify, analyse, evaluate and make suggestions for solving specific data-based issues. They must be able to argue for the relevance of the chosen theories, methods and models as well as for the proposed solution method. In addition, they must be able to reflect on the importance of the context in which the solution is included. Specifically, it is expected that after completion of the course the students will be able to:
  • Understand and apply a number of machine learning methods for knowledge detection in both un-structured and structured data examples
  • Understand and compare the algorithms behind different data mining and machine learning methods
  • Match and possibly combine methods for practical use in a reasonable context.


After completion of the course, the goal is that the students have acquired the competences to:
  • Make informed choices about the use of machine learning techniques
  • Parametrisise machine learning algorithms for a given data material
  • Design and develop a complete solution for a complex, realistic problem
  • Communicate and discuss the solutions with professionals and non-specialists.



Teaching methods and study activities

The mode of teaching will be classroom based and will involve lectures by the teacher and exercises made in class. The students are also expected to work on exercises both before and after classes. The total work-load for the student is expected be around 130 hours. Referring to the Study Activity Model, the workload is distributed at follows:
Approx. 50 hours or 40%
Participation of lecturer and students - Initiated by the lecturer
  • Lessons, scheduled
  • Project guidance
  • Exams and tests


65 hours or 50%

Participation of students - Initiated by the lecturer

  • Assignments, self-study
  • Project and group work
  • Homework and preparation for exams
  • Evaluation of the teaching
10 hours or 10 %
Participation of students - Initiated by students
  • Homework and preparation for exams
  • Self-study
  • Project work
  • Study groups
  • Literature search


All material will be uploaded to StudyNet.


The students must participate in a group assignment which will also constitute the foundation for the exam. While the assignment is not directly part of the final grade, it will have an indirect influence since the assignment will heavily effect the first part of the exam. If a student does not participate in the assignment, the student will not be able to attend the exam.
The course is graded internally according to the 7-scale.


​The course is evaluated based on two oral examinations.

The first examination is a group exam in which the students make a 10 minute presentation about their group assignment. This is followed by approx. 20 minutes of discussion between the students and the examiners. This discussion will evolve around two of the main topics of the course. The group examination takes a total of 30 minutes.

After the group exam, each student is then called for an individual 15 minute oral exam. This exam is a discussion about the two main topics that were not covered in the group examination. The student in not allowed to make a presentation at the individual oral exam. The 15 minutes include grading and feedback.

The student is given one grade based on both the group exam and the individual exam.


Grading criteria


Additional information



Richard Brooks

Valid from

2/1/2020 12:00:00 AM

Course type

6. semester
7. semester
Elective for the specialization Data Engineering


<div class="ExternalClassCCC2CA2EE72643E3ADC5C7A2D306FE12"><div></div><p>​</p></div>