Facts about the course
- ECTS Credits:
- Responsible department:
- Faculty of Computer Science, Engineering and Economics
- Course Leader:
- Roland Olsson
- Teaching language:
- ½ year
ITI41720 Machine Learning (Autumn 2021)
The course is connected to the following study programs
Elective course in the master programme in applied computer science full-time and part-time.
- Statistics and statistical programming
- Algorithms and data structures
First or third semester (autumn) in the full-time programme.
First, third or seventh semester (autumn) in the part-time programme.
The student's learning outcomes after completing the course
- is familiar with both the possibilities and advantages of employing the machine learning methods in the course, as well as possible problems that may be encountered and how to overcome them.
- knows how the algorithms presented in the course work and their characteristics, for example which problems they work best for, overfitting, expected accuracy and computational requirements, for example how much benefit that accelerators may provide.
Given a machine learning application, the student is able to
- determine which theory and which methods that are presented in the course that are relevant and also how to apply them.
- perform hyperparameter tuning or in some cases even perform modifications of the source codes.
- use at least one implementation for each of the major machine learning techniques that are taught in the course.
- is able to independently read machine learning papers and other literature and evaluate what works well and what does not for new problems.
- knows the terminology of machine learning and is familiar with the mathematics that is common in the field.
- knows the general behaviour of machine learning methods for example regarding how much data that is required, how to preprocess the data and ensure that its quality is sufficient.
This course gives an advanced insight into the main methods used in machine learning. The topics covered in this course are:
- Concepts related to basic types of learning (supervised, unsupervised, reinforcement): preprocessing, feature extraction, overfitting, error functions.
- Decision and regression trees, random forest and XGBoost
- Artificial neural networks, deep learning.
- Optimization (evolutionary algorithms and other search methods)
- Bayesian inference / classification.
Ethics and privacy in machine learning is also mentioned.
Additionally, the course contains up to date topics that are not known when this text is being written.
Forms of teaching and learning
The students will learn by attending lectures, read the books, papers and online material in the course reading list and above all by working on two projects. The project work is supervised each week and results in a 10 pages report for each project. These reports are part of the examination in the course.
Approx. 280 hours.
Coursework requirements - conditions for taking the exam
The student must have finished both of their projects.
Coursework requirements must be accepted to qualify for the exam.
Portfolio and individual written exam
The exam consists of both a portfolio and an individual written exam.
The portfolio (determines 65% of the final grade) consists of two projects. The projects can be carried out individually or in groups of two students. The students will get an individual grade.
The individual written exam determines 35% of the final grade and focuses on theory. Duration 3 hours. No supporting materials allowed.
Both parts of the exam must be passed to pass the exam as a whole. The student will get an individual joint grade for the entire course. Grades: A - F.
External and internal examiner, or two internal examiners.
Conditions for resit/rescheduled exams
Upon re-examination, each part of the examination can be retaken.
This course is evaluated by a
- Mid-term evaluation (compulsory)
The responsible for the course compiles a report based on the feedback from the students and his/her own experience with the course. The report is discussed by the study quality committee of the faculty of Computer Sciences.
Last updated 22.10.2020. The reading list may be subject to changes before 1st of June 2021.
Books, papers and online materials posted on the learning platform.