Arvutiteaduse instituut
Courses.cs.ut.ee Arvutiteaduse instituut Tartu Ülikool
  1. Kursused
  2. 2026/27 sügis
  3. Masinõpe (MTAT.03.227)
EN
Logi sisse

Masinõpe 2026/27 sügis

  • Main
  • Lectures
  • Practice sessions
  • Homeworks
  • Projects
  • Paper summary
  • Grades
  • Links

Homework submission

Please review the following rules before submitting your assignment:

  1. Please submit only the .ipynb file exported from Google Colab.
  2. Run all homework exercises before submitting. The output should be present; preferably, restart the runtime and run all cells before submission.
  3. Do not change the descriptions of tasks shown in red, even if there is a typo, mistake, etc.
  4. Please avoid unnecessarily long printouts.
  5. Each task should be solved directly under the corresponding question and not elsewhere.
  6. Solutions to both regular and bonus exercises should be submitted in a single IPYNB file.

Note: Late days will be used automatically if you submit after the deadline unless you let us know in advance.

HW1 - supervised learning (Deadline: 20.09.2026)

You can find tasks for the first homework in the following colab.

Lahenduste esitamiseks peate olema sisse loginud ja kursusele registreerunud.

HW2 - unsupervised learning (Deadline: 04.10.2026)

HW2 will be made available on September 21.

HW3 - deep learning (Deadline: 18.10.2026)

HW3 will be made available on October 5.

Project plan (Deadline: 11.10.2026)

Project plan submission will be made available before the deadline.

Paper summary (Deadline: 48 hours before the booked discussion)

Choose a seminal ML paper, write a two-page summary, and discuss it with the assigned instructor. Here you should submit the summary in PDF format at least 48 hours before your appointment. Detailed instructions and booking links.

Lahenduste esitamiseks peate olema sisse loginud ja kursusele registreerunud.

HW4 - regularisation learning (Deadline: 01.11.2026)

HW4 will be made available on October 19.

HW5 - ensemble learning (Deadline: 15.11.2026)

HW5 will be made available on November 2.

HW6 - performance metrics (Deadline: 06.12.2026)

HW6 will be made available on November 23.

Team evaluation (Deadline: 20.12.2026)

Team evaluation will be made available before the deadline.

  • Arvutiteaduse instituut
  • Loodus- ja täppisteaduste valdkond
  • Tartu Ülikool
Tehniliste probleemide või küsimuste korral kirjuta:

Kursuse sisu ja korralduslike küsimustega pöörduge kursuse korraldajate poole.
Õppematerjalide varalised autoriõigused kuuluvad Tartu Ülikoolile. Õppematerjalide kasutamine on lubatud autoriõiguse seaduses ettenähtud teose vaba kasutamise eesmärkidel ja tingimustel. Õppematerjalide kasutamisel on kasutaja kohustatud viitama õppematerjalide autorile.
Õppematerjalide kasutamine muudel eesmärkidel on lubatud ainult Tartu Ülikooli eelneval kirjalikul nõusolekul.
Courses’i keskkonna kasutustingimused