Table of contents

The course is connected to the following study programs

Teaching language

English

Learning outcomes

The student will get in-depth knowledge of selected advanced topics in Tsetlin machines, obtaining both theoretical and practical skills. The student will further be able to analyse, implement, and evaluate the main Tsetlin machine architectures, including regression, convolution, auto-encoding, and composites. Finally, the student will know how to apply the architectures within image analysis, natural language processing, and board games.

Contents

The course is organized into five modules.

  1. The Tsetlin Automaton and Games of Tsetlin Automata. This module covers the foundation for Tsetlin machines, namely, the Tsetlin automata and games of automata. Apart from the analysis of individual Tsetlin automata, collectives of Tsetlin automata are studied through game theory.
  2. The Tsetlin Machine - Inference and Learning. This module introduces the vanilla Tsetlin machine, including booleanization, clauses, voting, and learning with feedback Type I and II.
  3. Selected Applications in Natural Language Processing, Image Analysis, Board Games, and Edge Computing. We here look in detail at selected application areas, covering how to booleanize the input, design the model, and interpret the learning outcome.
  4. Markov Chain Analysis of Learning Process. This module focuses on Markov chain analysis in combination with game theory to study the convergence of Tsetlin machine learning.
  5. Advanced Architectures: Regression, Convolution, Auto-encoding, and Composites. The final module addresses the analysis, design, and application of more advanced architectures, including regression, convolution, auto-encoding, and composites.

Teaching and learning 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.

Examinations

Graded portfolio assessment.

Information about the content of the portfolio will be given in Canvas by the start of the semester. There will not be arranged a postponed exam for the portfolio.

Student 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 a free-standing course

Yes, if there are places available

Admission Requirement if given as a free-standing course

Admission requirements for the course are the same as for the master’s programme in ICT.
Last updated from FS (Felles studentsystem) Oct. 15, 2026 1:37:08 PM