Osion kuvaus

  • ML project is a series of small peer-graded assignments, where we will formulate real-life problem as a machine learning problem, by applying ML methods learnt during the course. Python implementation is optional.

    ML project is completed incrementally in three stages (40 points in total, see table below):

    • Stage 1. Machine learning – when and why? (7p max)
    • Stage 2. ML problem formulation – Data (11p max)
    • Stage 3. ML problem formulation – Model and Loss (22p max)

    Each stage includes a submission of a report and its peer grading. You will have an opportunity to improve project parts based on the feedback from peer-reviews and submit edited version in the next stage. Given time constrains and expected workload (2 credits = 54 hours), we do not ask to do any numerical experiments, but to identify appropriate problem, formulate it as ML problem and plan implementation details.


    Note, these three peer-graded assignments are mandatory!


    In addition, we will have two bonus tasks:

    • ML problem - Python implementation (points TBA)
    • Cost of ML project (points TBA)

    ML project time table and points:


    ML - when & why? 
    Problem formulation 
    DATA
    Problem formulation 
    MODEL & LOSS

    Points (submission + peer-grading)

    5 + 2 6 + 5
    14 + 8
    Submission opens
    5 June, 08:00
    19 June, 08:00
    3 July, 08:00
    Submission closes
    12 June, 23:59
    26 June, 23:59
    10 July, 23:59
    Peer review closes 
    19 June, 23:59
    3 July, 23:59
    17 July, 23:59
    Description
    Click here
    Click here
    Click here
    Grading criteria Click here   Click here Click here 

    The points achieved during each stage consist of two components:

    1. quality of your report, assessed by peer graders (students or course staff)
    2. quality of your review (e.g., gradings are well-justified)

    Before submission check "Grading criteria", these exact criteria are used for peer-grading.

    To get maximum points you must complete all the peer evaluations that will be assigned to you.