Computer Science, Advanced Technologies for Intelligent Systems, Second Cycle, 15 credits

Aims and objectives

General aims for second cycle education

Second-cycle courses and study programmes shall involve the acquisition of specialist knowledge, competence and skills in relation to first-cycle courses and study programmes, and in addition to the requirements for first-cycle courses and study programmes shall

• further develop the ability of students to integrate and make autonomous use of their knowledge
• develop the students' ability to deal with complex phenomena, issues and situations, and
• develop the students' potential for professional activities that demand considerable autonomy, or for research and development work.

(Higher Education Act, Chapter 1, Section 9)

Course objectives

Knowledge and understanding
Completing this course, the student shall be able to

• explain the fundamental concepts in machine learning and the different classes of machine learning algorithms,
• choose and motivate probabilistic methods for complex real-world problems in localization and map building,
• discuss the behavior and performance of these algorithms, based on their theoretical foundations.

Applied knowledge and skills
Completing this course, the student shall be able to

• prepare data and apply machine-learning methods to achieve a learning goal within an intelligent system,
• develop software that uses probabilistic techniques for robotics applications,
• assess the performance of the developed software.

Judgments and approach
Completing this course, the student shall be able to describe and explain the virtues and limitations of probabilistic and machine-learning approaches,and to identify problems or misleading results.

Main content of the course

Part 1: Machine Learning, 7,5 Credits

• core concepts and algorithms used for supervised and unsupervised learning,
• application of machine learning algorithms for the tasks of classification, prediction, and clustering,
• methods for data preprocessing including normalisation, feature extraction and selection, and dimensionality reduction,
• practical recommendations for applying machine learning algorithms, and
• evaluation and analysis of the performance of machine learning algorithms.

Part 2: Probabilistic Robotics, 7,5 Credits

• mathematical statistics: Bayes' theorem, probability distributions, generative and discriminative models,
• Kalman filters,
• particle filters and Monte Carlo optimisation,
• robot motion and sensor models, and
• SLAM (simultaneous localisation and mapping),
• data association,
• random fields,

Teaching methods

Part I: Machine Learning
Lectures, lab assignments, and seminars.

Part II: Probabilistic Robotics
Lectures, independent reading, group project work with supervision sessions.

In case of a small number of students, the lectures may be replaced by individual tutoring.

Students who have been admitted to and registered on a course have the right to receive tuition and/or supervision for the duration of the time period specified for the particular course to which they were accepted (see, the university's admission regulations (in Swedish)). After that, the right to receive tuition and/or supervision expires.

Examination methods

Part 1: Machine Learning

Machine Learning, Practice, 4.5 credits (Code: A001)
Written lab reports.

Machine Learning, Theory, 3 credits (Code: A002)
Oral seminar presentations.

Part 2: Probabilistic Robotics

Probabilistic Robotics, Theory, 3 credits (Code: A003)
Written examination. In case of a small number of students, the written examination may be replaced by oral examination.

Probabilistic Robotics, Practice, 4.5 credits (Code: A004)
Practical demonstration of group project results along with written and oral presentation.

For students with a documented disability, the university may approve applications for adapted or other forms of examinations.

For further information, see the university's local examination regulations (in Swedish).

Grades

According to the Higher Education Ordinance, Chapter 6, Section 18, a grade is to be awarded on the completion of a course, unless otherwise prescribed by the university. The university may prescribe which grading system shall apply. The grade is to be determined by a teacher specifically appointed by the university (an examiner).

According to regulations on grading systems for first- and second-cycle education (vice-chancellor's decision 2019-01-15, ORU 2019/00107), one of the following grades is to be used: fail, pass, or pass with distinction. The vice-chancellor or a person appointed by the vice-chancellor may decide on exceptions from this provision for a specific course, if there are special reasons.

Grades used on course are Fail (U), Pass (G) or Pass with Distinction (VG).

Machine Learning, Practice
Grades used are Fail (U), Pass (G) or Pass with Distinction (VG).

Machine Learning, Theory
Grades used are Fail (U) or Pass (G).

Probabilistic Robotics, Theory
Grades used are Fail (U), Pass (G) or Pass with Distinction (VG).

Probabilistic Robotics, Practice
Grades used are Fail (U), Pass (G) or Pass with Distinction (VG).

For further information, see the university's local examination regulations (in Swedish).

Comments on grades

To receive the grade VG for the entire course, the student must have VG for at least two of the examination methods.

Specific entry requirements

First-cycle degree of 180 credits, with Computer Science as the main field of study, and at least 15 credits in mathematics (analysis and algebra), or first-cycle degree of 180 credits, and at least 30 credits in mathematics (analysis and algebra), as well as at least 15 credits in Computer Science or Informatics (which includes programming). The applicant must also have qualifications corresponding to the course "English 6" or "English B" from the Swedish Upper Secondary School, as well as at least 7.5 credits from second-cycle courses that include programming or mathematical statistics.

For further information, see the university's admission regulations (in Swedish).

Transfer of credits for previous studies

Students who have previously completed higher education or other activities are, in accordance with the Higher Education Ordinance, entitled to have these credited towards the current programme, providing that the previous studies or activities meet certain criteria.

For further information, see the university's local credit transfer regulations (in Swedish).

Other provisions

The course is given in English.

Reading list and other teaching materials

Part 1: Machine Learning, 7,5 Credits

Additional Reading

Bishop, Christopher M. (2007)
Pattern Recognition and Machine Learning
Springer, ISBN: 9780387310732, 758 pages

Mitchell, Tom M. (1997)
Machine Learning
McGraw-Hill, ISBN: 9780071154673, 352 pages

Additional material will be made available during the course.

Part 2: Probabilistic Robotics, 7,5 Credits

Required Reading

Thrun, Sebastian, Burgard, Wolfram och Fox, Dieter (2005)
Probabilistic Robotics
MIT Press, 647 pages

Additional material will be made available during the course.