Machine Learning Seminar

COURSE SYLLABUS, third-cycle courses

ECTS/HP: 2 ECTS per semester (can be taken up to four times)

Course code:
SRT0008

Educational level: third-cycle course

Entry requirements:

• Basic knowledge in Machine Learning
• Admission to third-cycle studies involving Machine Learning or Machine Learning applications
• Fundamental knowledge in Scientific communication.

Course content:
The ML-group organize a weekly seminar and reading group for machine learning. Every other week there is a reading group meeting during which we discuss one or several papers that the participants should have read. For the reading groups sessions someone will lead the discussion and typically have prepared some discussion material. In the weeks between there is a seminar with one or more ML related topics.

Participation is possible in the whole seminar (reading group and seminar) or in either of them. ECTS are granted, upon participating in a minimum amount of sessions and:

• Giving a presentation about a recent ML work (either own PhD topic or review of a research paper) (1 ECTS)
• Participation in at least 5 discussion sessions and organizing a discussion session in the reading group, preparing a short summary presentation of the paper and leading a discussion with guided questions (1 ECTS)

Learning outcomes:

• demonstrate broad knowledge and systematic understanding of the research domain as well as advanced and up-to-date specialised knowledge in a limited area of Machine Learning
• demonstrate the capacity for scholarly analysis and synthesis as well as to review and assess new and complex phenomena, issues and situations autonomously and critically
• demonstrate the ability in national contexts to present and discuss research and research findings authoritatively in speech and in dialogue with the academic community

Course methods:
We have weekly meetings. Each participant selects a seminar topic to present and show the broad knowledge, as well as the up-to-date specialized knowledge; and a recent paper which has to be critically reviewed for the reading group. In practical meeting sessions, the work is presented and discussed with the other course participants as well as senior members of the Machine Learning group (and potentially other interested internal and external participants).

Examination form:
Oral presentation and discussion.

Grading scale: Pass/Fail

Course literature:
recent publications in machine learning and applications within the machine learning subject.

Education cycle:
Any stage of PhD studies

Course is given periodically: Yes □ Next time: Spring 2021

Send application to: maryam.pahlavan.nodeh@ltu.se
Doctoral student enter name, civic registration number, e-mail, Division and Department in the application

Deadline for application:
continuous participation possible

Course open for application by doctoral students admitted to other universities than LTU: Yes □

Limited number of students: No □

Tuition:
If the course is allocated resources via internal resource allocation system, the course is free of charge for doctoral students admitted at LTU, for doctoral students admitted to other universities, course fees may be required. For other courses the Department decides on course fees.

Contact person:
Rajkumar Saini (Rajkumar.Saini@ltu.se)

Examiner:
Marcus Liwicki

Course syllabus decided by:
Johan Carlson, Forskarutbildningsledare SRT, LTU-2638-2026

Date of decision: 2026-03-24