Stage-oe-small.jpg

Lehre/Seminar Knowledge Discovery and Data Mining: Unterschied zwischen den Versionen

Aus Aifbportal
Wechseln zu:Navigation, Suche
(8 dazwischenliegende Versionen von 3 Benutzern werden nicht angezeigt)
Zeile 1: Zeile 1:
 
{{Lehrveranstaltung
 
{{Lehrveranstaltung
|Lehrveranstaltungstype=Praktikum
+
|Lehrveranstaltungstype=Seminar
|Titel DE=Knowledge Discovery and Data Mining
+
|Titel DE=Knowledge Discovery and Data Science
|Titel EN=Knowledge Discovery and Data Mining
+
|Titel EN=Knowledge Discovery and Data Science
 
|Forschungsgruppe=Web Science
 
|Forschungsgruppe=Web Science
|Dozent=York Sure-Vetter; Achim Rettinger;
+
|Dozent=Michael Färber
|Übungsleiter=Steffen Thoma; Patrick Philipp;
+
|Übungsleiter=Tarek Saier
 
|Fach=Künstliche Intelligenz; Maschinelles Lernen; Data Science
 
|Fach=Künstliche Intelligenz; Maschinelles Lernen; Data Science
 
|Semester=SS
 
|Semester=SS
 
|LinkVVZ=http://ilias.studium.kit.edu
 
|LinkVVZ=http://ilias.studium.kit.edu
 
|LinkStudierendenportal=https://campus.studium.kit.edu
 
|LinkStudierendenportal=https://campus.studium.kit.edu
|Inhalt=Ziel des Praktikums KDDM ist die komplette Durchführung eines Data Mining Projekts. Dies beinhaltet die Datenaufbereitung, Modellierung, Berechnung sowie die Auswertung der MiningErgebnisse. Bewertet wird die praktische Umsetzung des Themas (Softwareentwicklung) sowie ein Abschlussvortrag und ein Bericht, der auch theoretische Grundlagen zum entsprechenden Data Mining Gebiet beinhalten soll. Beim ersten Termin wird ein Auswahl von Datensätzen und zugehörigen Aufgabe / Algorithmen vorgestellt. Außerdem werden Gruppen gebildet und Themen zu Gruppen zugeordnet. Denkbare Themen sind z.B. Empfehlungsdienste für Nachrichtenartikel; Analyse von Modellierungsunterschieden der Wikipedia Taxonomie in verschiedenen Sprachen; Zuordnung von Nachrichtenartikeln zu WikipediaKategorien; Erkennung dynamischer Fakten in der DBpedia, etc.
+
|Inhalt=This seminar will be given in English and will be provided by the research group "Web Science" (Institute AIFB; Dr. Michael Färber).
  
Die Gruppen können bei Interesse Aufgaben und Themen mitgestalten.
+
The aim of the Seminar "Knowledge Discovery and Data Science" is the implementation of a data science project. This includes the data preparation, modeling, computation, and scientific evaluation of the developed system.
|Literatur=Detaillierte Referenzen werden zusammen mit den jeweiligen Themen angegeben. Allgemeine Hintergrundinformationen ergeben sich z.B. aus den folgenden Lehrbüchern:
+
 
* Mitchell, T.; Machine Learning, McGraw Hill, 1997.  
+
The following aspects will be taken into consideration for the grade: (1) design and development of the system; (2) actual practical implementation (software engineering & development); (3) the final presentation; (4) the written report (Seminararbeit), which should also contain the necessary theoretical foundations for explaining the software project and the implemented system.
* Cook, D.J. and Holder, L.B. (Editors) Mining  Graph Data, ISBN: 0-471-73190-0, Wiley,
+
 
* Manning, C. and Schütze, H.; Foundations of Statistical NLP, MIT Press, 1999.
+
Note that this seminar focuses on the design and implementation of a research prototype system. Thus, all participating students should have good programming skills (backend and/or frontend) and some experience in data processing. Please indicate in the motivation letter when applying for this seminar, which skills you can bring in and extend in the frame of the seminar's project.
 +
 
 +
At the first meeting at the start of the semester, a selection of projects will be presented, together with an overview of the tasks to be solved and the data sets which can be used. Then, groups of 2-3 people will be formed and each group will work on one project.
 +
 
 +
Potential topics are located in the field of data science, machine learning, natural language processing, and semantic web. One can imagine topics like
 +
 
 +
* building a recommender system which can recommend which publications to read and to cite;
 +
* building a recommender system which can recommend which machine learning approach to use and why;
 +
* extracting information from texts and modeling it semantically for a semantic search system;
 +
* building a knowledge graph for product recommendation;
 +
* automatically determining the bias of news articles;
 +
* automatically determining based on news articles which city is affected by the coronavirus;
 +
* ...
 +
 
 +
All students will be given the chance to write a scientific publication together with the supervisor based on the project's outcomes (i.e., seminar report). In this way, students will gain international visibility in the area of data science and machine learning, which might be beneficial for future applications and career paths. We particularly encourage female students to apply for this seminar.
 +
 
 +
The kick-off event will take place on April 27, 2020 (to be confirmed!).
 +
 
 +
Interested? Then apply here:
 +
* https://portal.wiwi.kit.edu/ys/3340 (for Master students)
 +
* https://portal.wiwi.kit.edu/ys/3341 (for Bachelor students)
 +
|Literatur=Relevant literature will be given after project assignment.
 
}}
 
}}
 
[[Kategorie:Aktive_Lehrveranstaltung]]
 
[[Kategorie:Aktive_Lehrveranstaltung]]

Version vom 22. Juli 2021, 16:06 Uhr

Seminar Knowledge Discovery and Data Science

Details zur Lehrveranstaltung
Dozent(en) Michael Färber
Übungsleiter Tarek Saier
Fach (Gebiet) Künstliche IntelligenzMaschinelles LernenData Science
Leistungspunkte ECTS
Erfolgskontrolle
Semester SS


Aktuelle und ergänzende Informationen, sowie Zeiten und Räume der Lehrveranstaltung finden Sie im Vorlesungsverzeichnis der Universität.
Link zum Vorlesungsverzeichnis
Link zum Studierendenportal


Forschungsgruppe


Inhalt

This seminar will be given in English and will be provided by the research group "Web Science" (Institute AIFB; Dr. Michael Färber).

The aim of the Seminar "Knowledge Discovery and Data Science" is the implementation of a data science project. This includes the data preparation, modeling, computation, and scientific evaluation of the developed system.

The following aspects will be taken into consideration for the grade: (1) design and development of the system; (2) actual practical implementation (software engineering & development); (3) the final presentation; (4) the written report (Seminararbeit), which should also contain the necessary theoretical foundations for explaining the software project and the implemented system.

Note that this seminar focuses on the design and implementation of a research prototype system. Thus, all participating students should have good programming skills (backend and/or frontend) and some experience in data processing. Please indicate in the motivation letter when applying for this seminar, which skills you can bring in and extend in the frame of the seminar's project.

At the first meeting at the start of the semester, a selection of projects will be presented, together with an overview of the tasks to be solved and the data sets which can be used. Then, groups of 2-3 people will be formed and each group will work on one project.

Potential topics are located in the field of data science, machine learning, natural language processing, and semantic web. One can imagine topics like

  • building a recommender system which can recommend which publications to read and to cite;
  • building a recommender system which can recommend which machine learning approach to use and why;
  • extracting information from texts and modeling it semantically for a semantic search system;
  • building a knowledge graph for product recommendation;
  • automatically determining the bias of news articles;
  • automatically determining based on news articles which city is affected by the coronavirus;
  • ...

All students will be given the chance to write a scientific publication together with the supervisor based on the project's outcomes (i.e., seminar report). In this way, students will gain international visibility in the area of data science and machine learning, which might be beneficial for future applications and career paths. We particularly encourage female students to apply for this seminar.

The kick-off event will take place on April 27, 2020 (to be confirmed!).

Interested? Then apply here:


Literatur

Relevant literature will be given after project assignment.