Arvutiteaduse instituut
  1. Kursused
  2. 2018/19 sügis
  3. Andmekaeve uurimisseminar (MTAT.03.277)
EN
Logi sisse

Andmekaeve uurimisseminar 2018/19 sügis

Older Datamining Seminars: 2010k » 2011k » 2012s » 2014k » 2014s » 2015k » 2015s » 2016k » 2016s » 2017k » 2017s

  • About
  • Supervisors
  • Topics
  • Presentations
  • Assignments
  • Deadlines

Assignments

StudentSupervisorTopic
Hristijan SardjoskiMeelis KullActivity recognition from accelerometers in SPHERE
Hele-Andra KuulmetsSven LaurPhrase similarity measures that are robust to word order
Maksym SemikinTambet MatiisenSequence-aware recommendation system
Kristjan VeskimäePeep KüngasTrade credit limit estimation with machine learning
Kevin KanarbikJaak Übi, Rajesh SharmaAn investigation on the relationship between inequality and growth
Simona MicevskaSherif SakrAutomated change detection in large datasets
Sebastian VärvAmnir HadachiTravel time estimation based on raw GPS data
Sriyal jayasingheKairit SirtsDeep learning based textual entailment system for Sinhala language to support short answer grading
Nesma AlmoazamySherif SakrBenchmarking Deep Learning frameworks using CNN over various datasets
Tõnis OjanduEzequiel ScottUnderstanding team performance in agile software development
Mansur AlizadaPENDINGPENDING
Novin ShahroudiMeelis KullLong-Horizon Forecasts with Expectation-Biased LSTM Networks

Reasearch plan

StudentReceivedDefended
Hele-Andra KuulmetsOKOk
Tõnis OjanduOKFAIL
Novin ShahroudiOKOk
Sriyal jayasingheOKOk
Maksym SemikinOKOk
Kristjan VeskimäeOKOk
Kevin KanarbikOKOk
Sebastian VärvOKOk
Simona MicevskaOKOk
Hristijan SardjoskiOKOk
Nesma AlmoazamyOKOk

Defending assignments

  • Natural Language processing
    • Sriyal jayasinghe (Mark Fishel, Kairit Sirts)
    • Hele-Andra Kuulmets (Kairit Sirts, Sven Laur)
  • Deep Neural Nets
    • Maksym Semikin (Sven Laur, Tambet Matiisen)
    • Nesma Almoazamy (Meelis Kull, Tambet Matiisen)
    • Novin Shahroudi (Sven Laur)
  • Prediction tasks
    • Kristjan Veskimäe (Meelis Kull)
    • Sebastian Värv (Dmytro Fishman)
    • Hristijan Sardjoski (Dmytro Fishman)
  • Feature extraction and descriptive analysis
    • Tõnis Ojandu (Sven Laur)
    • Kevin Kanarbik (Sven Laur)
  • Change detection and transfer learning
    • Simona Micevska (Meelis Kull)

Reviewing tasks

The following table describes which persons you need to review. So find your row and review the persons who are in this row.

StudentReviewer 1Reviewer 2Extra eviewer
Hele-Andra KuulmetsSriyal jayasingheSebastian Värv 
Novin ShahroudiMaksym SemikinHele-Andra Kuulmets 
Sriyal jayasingheHele-Andra KuulmetsSimona Micevska 
Maksym SemikinNovin ShahroudiSriyal jayasinghe 
Kristjan VeskimäeHristijan SardjoskiSimona Micevska 
Sebastian VärvHristijan SardjoskiNesma Almoazamy 
Simona MicevskaKristjan VeskimäeMaksym Semikin 
Hristijan SardjoskiSebastian VärvNesma Almoazamy 
Nesma AlmoazamyNovin ShahroudiKristjan Veskimäe 

Reviewing guidlines

  • Review is not a listing of grammar errors
  • Review is a listing of logical errors and ideas to pursue further
  • It is ok to say in the review that you did not understand certain paragraphs or concepts
  • Review should give suggestion in terms of presentation of ideas and layout
  • Review should contain a clear opinion about the work you are reviewing
  • Still be polite and write the review in the form you would like to receive

First write a short paragraph describing the work as a whole. Write what is good and bad in it and derive your final judgement about the work. Next fill the following reviewing form. This review form contains questions that provide a framework to structure you critical comments into separate blocks. So use those question sections to convey your critical comments about the work. SPage linktrong? A good review mostly discards all grammar mistakes and deals with presentation and content. Try to write something that yourself would find instructive if you were an author. In particular, mark all places which you cannot understand or which seem illogical to you as a reader. For those of you who have not done it before, there is a longer Estonian tutorial how to review. It is a long text and covers different reviewing levels so do not implement all suggestions. Send the final review to me and the person who you are reviewing. If you do not know the mail address of the author send it only to me. I will forward it.

  • I will not accept reviews that contains only a listing of grammar errors
  • I will not accept reviews that have no clear opinion about the work
  • The opinion can be completely wrong or unfair as long as it is justified

Presentations

13th Decembrer 14:15 @ Liivi 2-511

  • Simona Micevska
  • Hristijan Sardjoski
  • Sriyal Jayasinghe
  • Nesma Almoazamy

20th Decembrer 14:15 @ Liivi 2-511

  • Kristjan Veskimäe
  • Sebastian Värv
  • Maksym Semikin
  • Hele-Andra Kuulmets
  • Novin Shahroudi

Progress

StudentInitial draftFirst draftReviewsFinal report
Hele-Andra KuulmetsOKOKOKOK
Tõnis OjanduOkFAIL----
Novin ShahroudiOKOKOKOK
Sriyal jayasingheOKOKOKOK
Maksym SemikinOKOKOKOK
Kristjan VeskimäeOKOKOKOK
Kevin KanarbikOKFAIL----
Sebastian VärvOKOKOKOK
Simona MicevskaOKOKOKOK
Hristijan SardjoskiOKOKOKOK
Nesma AlmoazamyOKOKOKOK
  • 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