Arvutiteaduse instituut
  1. Kursused
  2. 2015/16 sügis
  3. Andmekaeve uurimisseminar (MTAT.03.277)
EN
Logi sisse

Andmekaeve uurimisseminar 2015/16 sügis

Older Datamining Seminars: 2008k » 2008s » 2009k » 2009s » 2010k » 2011k » 2012s » 2014k » 2014s » 2014k

  • About
  • Track I: Deep Learning for NLP
    • Timetable
    • Creating tests
    • Project ideas
    • Projects
    • Keras
  • Track II: Research Projects
    • Presentations
    • Assignments
    • Deadlines

Projects

A project consists of a report and a presentation. Report should be about 5 pages and has to contain following sections:

  1. Introduction - description of the task and why it is important,
  2. Background - briefly mention previous work or classical methods usually applied to the task,
  3. Dataset - describe the dataset you used - how many samples, how many features, how did you collect it etc.,
  4. Method - describe the method you used - what kind of network was used, how many layers, how many nodes etc.,
  5. Results - provide the training plots and resulting tables,
  6. Discussion - brief analysis of the results - in what cases it worked when not,
  7. Future work - provide some ideas how to improve the results or for further experiments,
  8. Conclusion - summarize the report in one paragraph.

Presentation should be 10 minutes + 5 minutes for questions.

Presentations will be held on Monday 25th of January 2016 at 12 in J. Liivi 2-512 (the usual class time). Deadline for submitting the reports is Friday 29th of January 2016.

Final projects:

  • "Generating texts in Estonian language" - Robert Roosalu (slides) (report)
  • "Sentiment classification" - Aqeel Labash (slides) (report)

Other interesting works:

  • "Generating PhD thesises" - Kaido Lepik (report)
  • "Character based text prediction using Keras" - Lauri Tammeveski (report)
  • "Classifying business process execution traces with LSTM" - Irene Teinemaa (report)
  • "Positioning rat using neuronal activity in hippocampus" - Tambet Matiisen (slides)
  • 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