This course is intended as a first course in machine learning (ML) for students intending to become ML-experts. In the course, you will gain a broad overview of the theory and practice in machine learning across different areas and perspectives. Special emphasis is placed on teaching connections and how everything in ML fits together, as well as "learning by doing". A big part of the course is solving machine learning problems and comparing solutions, both on your own and together with your fellow machine-learning experts-to-be at KTH. The goal is to give you a solid theoretical and practical foundation to stand on for taking advanced machine-learning courses at KTH, and to prepare you for a career as a ML practitioner.
Choose semester and course offering to see current information and more about the course, such as course syllabus, study period, and application information.
KTH Campus
Autumn 2026: P1 (7.5 hp)
50%
10737
Normal Daytime
English
Min: 1
Please note: all information from the Course syllabus is available on this page in an accessible format.
Course syllabus DD1420 (Autumn 2026–)Important subjects in the course include:
− 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
in order to
− be able to define problems in data analysis clearly
− formulate an appropriate maskinlärningslösning and strengthen this solution through critical and quantitative evaluation
− be well prepared to read advanced courses in machine learning.
Knowledge in linear algebra, 7.5 credits, equivalent to completed course SF1624/SF1672/SF1684.
Knowledge in multivariable analysis, 7.5 credits, equivalent to completed course SF1626/SF1674/SF1686.
Knowledge in probability theory and statistics, 6 credits, equivalent to completed course SF1910-SF1925/SF1935 or completed course component TEN1 within SF1910/SF1925/SF1935.
Knowledge and skills in programming, 6 credits, equivalent to completed course DD1337/DD1310-DD1319/DD1321/DD1331/DD1333/DD100N/ID1018/ID1022.
Knowledge of algorithms, data structures and basic software development techniques, 6 credits, equivalent to completed course DD1338/DD1320-DD1328/DD2325/ID1020/ID1021 or completed course components KONT and LABD in DD1326.
Based on recommendation from KTH’s coordinator for disabilities, the examiner will decide how to adapt an examination for students with documented disability.
The examiner may apply another examination format when re-examining individual students.
If the course is discontinued, students may request to be examined during the following two academic years.
The earlier course module TES1 is replaced by KON1 and PRO1 is replaced by ÖVN1, and INL1 is replaced by INLM.
The courses DD1420 and DD2421 overlap with regard to their contents.
One can not recieve credit for both courses.
