Facts about the course

ECTS Credits:
7.5
Responsible department:
Faculty of Logistics
Course Leader:
Anna Konovalenko
Lecture Semester:
Autumn
Teaching language:
English
Duration:
½ year

IBE400 Machine Learning (Autumn 2021)

About the course

The course reviews the most important theories and techniques for machine learning, as a systematic method for analyzing big data sets. It gives an introduction to machine learning, which is computing systems that can learn from own experiences and solve complex problems in various situations. The course shows how the increase in processing power, storage capacities and access to large datasets, contributes to new uses for machine learning, and it gives an introduction to the methods machine learning uses to analyse big data, finding patterns and relations, and learn from these without human invervention. In the exercises, machine learning is used on real data sets from a model company, in combination with well known systems that are used in industry for such purposes.

The course is connected to the following study programs

  • Individual Study Courses/Part- time studies
  • Bachelor in IT and Digitalization

Recommended requirements

You should have basic skills in programming and mathematics similar to IBE151 and MAT100

The student's learning outcomes after completing the course

Students will after passed examination, have an overview and user experience with decision trees, regression analysis, different uses of classifications and clusters, exceptions, neural networks and biologically inspired optimization. They shall also know challenges in using these techniques in practical settings, and cost-benefit considerations in machine learning, compared to other ways to solve the same problems, including advanced numerical methods.

The student will after passing this course, be able to

  • describe the machine learning methods of regression, classification and ranking.

  • give examples of machine learning algorithms in regression, classification and ranking

  • describe areas of use for regression, classification and ranking algorithms

  • use machine learning algorithms in one or more of the most common software libraries made for this purpose.

Forms of teaching and learning

4 hours lecture per week with lectures, seminars, project work and assistance from course assistants and course teacher. 

Coursework requirements - conditions for taking the exam

  • Mandatory coursework: Assignment(s)

  • Courseworks given: 2

  • Courseworks required: 2

 

Examination

  • Form of assessment: Written school assessment

  • Proportion: 100%

  • Duration: 4 Hours

  • Grouping: Individual

  • Grading scale: Letter (A - F)

  • Support material: All printed and written supporting material + calculator with empty memory

 

Syllabus

Pensumoversikt

Last updated from FS (Common Student System) Oct. 28, 2021 12:20:17 AM