Program Overview

Course Overview

The course DD1420, Foundations of Machine Learning, is a 7.5 credit course intended as a first course in machine learning for students intending to become machine learning experts. The course provides a broad overview of the theory and practice in machine learning across different areas and perspectives, with special emphasis on teaching connections and how everything in machine learning fits together, as well as "learning by doing".

Information per Course Offering

The course is offered in different semesters, including Autumn 2025, Spring 2026, and Autumn 2026. For the Spring 2026 course offering, the following information is available:

• Course location: KTH Campus
• Duration: 13 January 2026 - 13 March 2026
• Periods: Spring 2026: P3 (7.5 hp)
• Pace of study: 50%
• Application code: 61431
• Form of study: Normal Daytime
• Language of instruction: English
• Target group: Open to students in year 3 and for students admitted to a master's programme as long as it can be included in their programme.

Course Syllabus

The course syllabus is available as a PDF document. The syllabus includes information about the course contents, intended learning outcomes, and examination.

Content and Learning Outcomes

The course covers important subjects in machine learning, including:

• What is machine learning?
• Optimisation
• Generalisation
• Machine Learning theory
• Neural networks and deep learning
• Geometry in machine learning
• Kernel methods
• Probabilistic methods in machine learning
• Information theory in machine learning
• Machine learning for data synthesis

After passing the course, the student shall be able to:

• Use basic concepts, language, and notation that supports machine learning
• Use mathematical and statistical methods that support machine learning
• Derive and prove selected theoretical results
• Implement basic machine learning models
• Interpret the results to apply machine learning models on data
• Discuss how one can solve practical machine learning problems

Literature and Preparations

The course has specific prerequisites, including:

• Knowledge in algebra and geometry, 7.5 higher education credits
• Knowledge in multivariable analysis, 7.5 higher education credits
• Knowledge in probability theory and statistics, 7.5 higher education credits
• Knowledge and skills in programming, 6 credits
• Knowledge in algorithms and data structures, at least 6 higher education credits

Examination and Completion

The course is examined through:

• Digital quizzes, 3.0 credits
• Digital assignments with oral comprehension questions, 3.0 credits
• Exercises, 1.5 credits

The grading scale is A, B, C, D, E, FX, F. The examiner may apply another examination format when re-examining individual students.

Further Information

The course is offered by EECS/Intelligent Systems, and the main field of study is Technology. The education cycle is the first cycle. The course room in Canvas provides further information about the implementation of the course. The courses DD1420 and DD2421 overlap with regard to their contents, and one cannot receive credit for both courses.