Topic outline


  • Overview of the course:


    Machine learning is one of the cornerstone technologies in bioinformatics, used in numerous tools and applications. This course probes the state of the art in selected machine learning problems and the associated methods in bioinformatics, through introductory lectures and project work. The introductory lectures present and overview of the problem domain, and the set of methods to be applied in the projects.

    • Prerequisite knowledge: Machine learning: Basic principles or equivalent knowledge
    • Extent of the course: 5 ECTS
    • Grading: (0-)1-5
    • Course assistant: 
    • Teacher in charge: Prof. Harri Lähdesmäki Prof. Juho Rousu
    • Instructors: Anna Cichonska, Emmi Jokinen, Mehdi Saman Booy, ...

    Course components 

    The course is completed by the following components:

    • Following the lectures 1-4, (1 absence allowed, further absences can be paid by completing additional tasks)
    • Learning diaries from lectures 1-4 (required component, graded pass/fail)
    • Regular meetings with the instructor during the project work (weekly, unless otherwise agreed with the instructor)
    • Peer review of two other reports (required component, graded pass/fail)
    • Poster presentation (graded 1-5, weight 33%)
    • Final report (graded 1-5, weight 67%)

    Schedule (tentative)

    • First lecture: 08.03
    • Lecture 1: 08.03, Anna Cichonska 
    • Lecture 2: 15.03, Mehdi Saman Booy
    • Lecture 3: 22.03, Emmi Jokinen
    • Project topics published: 29.03
    • Project topics selection deadline: 01.04
    • Project work: 01.04-31.05
    • Poster session: 10.05 at 12:15 in T3 or CS building lobby (near main entrance)
    • Preliminary report dl: 15.05
    • Peer review dl: 22.05
    • Final report dl: 29.05

    Lectures

    Fridays 12-14, Room T3

    08.03-29.03: Topic presentations from Anna, Emmi, Mehdi, 

    Meetings with instructors

    29.03-29.05, once a week or according to mutual agreement

    Guidelines

    Guidelines for preparing learning diaries, project report, peer reviews and poster presentation can be found from the last year's course web page here.