IKT457 Learning Systems
- ECTS Credits:
- 7.5
- Responsible department:
- Faculty of Engineering and Science
- Course Leader:
- Ole-Christoffer Granmo
- Lecture Semester:
- Autumn
- Teaching language:
- English
- Duration:
- 1 term
The course is connected to the following study programs
- Artificial Intelligence and The Internet of Things, Master's Programme
- Artificial Intelligence, 5-year master programme
Teaching language
EnglishCourse contents
This course gives an advanced introduction to techniques for constructing learning systems, such as bandit algorithms, learning automata, Tsetlin machines, Thompson sampling, and various forms of Bayesian learning and reasoning. Furthermore, the course covers techniques within intelligent data analysis and pattern recognition. Applications within natural language processing, image analysis, and optimization will be emphasized.
Learning outcomes
After completion of the course, the students should be able to
- Implement on-line learning algorithms, including bandit algorithms, learning automata, Tsetlin machines, Thompson sampling, and various kinds of Bayesian learning.
- Analyse and evaluate learning systems empirically.
- Design and implement decentralized learning systems.
- Solve complex learning systems tasks, such as optimization, prediction, and classification.
- Understand and make use of probability theory to build and reason with learning systems
- Appreciate the difference between correlation- and causality-based models
- Build and reason with complex causal models in the form of Bayesian networks.
- Cast traditional problems in a learning systems perspective
Teaching methods
The course is organized with a combination of lectures, assignments, paper studies, labs, and report writing. The tasks are done individually or in small groups with group supervision. The workload for the average student is approximately 200 hours.
Evaluation
The person responsible for the course decides, in cooperation with student representative, the form of student evaluation and whether the course is to have a midway or end of course evaluation in accordance with the quality system for education, chapter 4.1.
Offered as Single Standing Module
Yes, if there are places available
Admission Requirement if given as Single Standing Module
Admission requirements for the course are the same as for the master’s programme in ICT.
Assessment methods and criteria
Graded portfolio assessment. Information about the content of the portfolio will be given in Canvas at the start of the semester for each seminar.