Arvutiteaduse instituut
  1. Kursused
  2. 2022/23 sügis
  3. Masinõpe (MTAT.03.227)
EN
Logi sisse

Masinõpe 2022/23 sügis

  • Main
  • Lectures
  • Practice sessions
  • Homeworks
  • Projects
    • Finished projects
  • Paper summary
  • Links

Lectures

Zoom link to lectures: (log into courses to see link)
Lectures are held every week on Monday at 10:15 in room 1037.

The following schedule is subject to change.

Lecture #DateTitleSlidesRecording
Lecture 01September 5Course organisation + Supervised learning (part I)PDF, PDFmp4
Lecture 02September 12Supervised learning (part II) + KahootPDFmp4
Lecture 03September 19Unsupervised learning (part I)PDFmp4
Lecture 04September 26Unsupervised learning (part II) + KahootPDFmp4
Lecture 05October 3Deep learning (part I)PDFmp4
Lecture 06October 10Deep learning (part II) + KahootPDFmp4
Lecture 07October 17Regularisation methods (part I)PDFmp4
Lecture 08October 24Regularisation methods (part II) + KahootPDFmp4
Lecture 09October 31Ensemble learning (part I)PDFmp4
Lecture 10November 7Ensemble learning (part II) + KahootPDFmp4
Lecture 11November 14 - 16Intermediate project presentations
Lecture 12November 21Performance metrics (part I)PDFmp4
Lecture 13November 28Performance metrics (part II) + KahootPDFmp4
Lecture 14December 5Guest talk: Machine learning for musical data (Anna Aljanaki)mp4
Lecture 15December 12 - 14Final project presentations TBA

Guest talk: Machine learning for musical data (Anna Aljanaki)

Music information retrieval is an area of applied machine learning, that both has practical applications (streaming services, production music catalogues) and has a suitable complexity and amount of unsolved problems to serve as benchmarking playground for SOTA AI from NLP, image processing and other domains. In the lecture we will look at a range of practical applications in MIR field in music categorization, recommendation, generation, OMR, and look closely at how SOTA NLP is applied to music

Last year's guest talk: Reinforcement Learning by Ilya Kuzovkin from OffWorld

Slides and the recording.

  • 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.
Tartu Ülikooli arvutiteaduse instituudi kursuste läbiviimist toetavad järgmised programmid:
euroopa sotsiaalfondi logo