Machine Learning

Level of Study

Bachelor

Teaching semester

Spring

Objectives and Content

The course introduces Machine Learning, with a view towards data analysis applications. Topics covered are supervised learning (classification and regression), unsupervised learning including clustering, decision tree learning, Bayesian learning, and working with textual data.

Learning Outcomes

A student who has completed the course should have the following learning outcomes defined in terms of knowledge, skills and general competence:

Knowledge

The candidate

• has theoretical knowledge about the principles of machine learning
• has a basic understanding of the contemporary machine learning algorithms
• has a broad knowledge about the use of machine learning in data analysis, its advantages and limitations

Skills

The candidate

• can analyze and design machine learning solutions for data analysis applications

Required Previous Knowledge

INFO132 or equivalent. Basic understanding of programming and algorithms.

Recommended Previous Knowledge

INFO132 or equivalent. Basic understanding of programming and algorithms.

Credit Reduction due to Course Overlap

INF264 (10 ECTS)

Access to the Course

The course is open to all students at the University of Bergen.

Teaching and learning methods

Lectures, seminars and data labs, normally 2 + 2 hours per week for 12-15 weeks.

Compulsory Assignments and Attendance

• Compulsory assignments, which have to be approved in the teaching semester.
• Participation: compulsory attendance at labs (at least 75%).

Approved compulsory requirements are valid for the two following semesters.

Update: In the spring semester 2021, the requirement to attend 75% of the seminars will not apply due to the corona situation. However, it is highly recommended that students attend as much as possible.

Forms of Assessment

4 hour written exam.

Update spring 2021: As part of the measures to limit the risk of corona infection the form of assessment will be:

• Group assignment where students demonstrate their ability to analyze and design machine learning solutions (30% of grade)
• 2 hour digital home exam (70% of grade)

Examination Support Material

All written material in paper form is allowed on the exam.

Grading Scale

The grading system has a descending scale from A to E for passes and F for fail.

Assessment Semester

Assessment in teaching semester and in the following semester (for the students who have valid compulsory assignments and attendance).

Course Evaluation

All courses are evaluated according to UiB's system for quality assurance of education.