Universität Wien

052300 VU Foundations of Data Analysis (2021S)

6.00 ECTS (4.00 SWS), SPL 5 - Informatik und Wirtschaftsinformatik
Prüfungsimmanente Lehrveranstaltung
Moodle

An/Abmeldung

Hinweis: Ihr Anmeldezeitpunkt innerhalb der Frist hat keine Auswirkungen auf die Platzvergabe (kein "first come, first served").

Details

max. 50 Teilnehmer*innen
Sprache: Englisch

Lehrende

Termine (iCal) - nächster Termin ist mit N markiert

Please use the following link to the first virtual meeting on March, 3 if you have no Moodle access.

https://univienna.zoom.us/j/93101135920?pwd=ZnRBMG9IQ28rdVdCU0s0YTB3V2Y2Zz09

Meeting-ID: 931 0113 5920
access code: 752028

  • Mittwoch 03.03. 09:45 - 11:15 Digital
  • Donnerstag 04.03. 09:45 - 11:15 Digital
  • Mittwoch 10.03. 09:45 - 11:15 Digital
  • Donnerstag 11.03. 09:45 - 11:15 Digital
  • Mittwoch 17.03. 09:45 - 11:15 Digital
  • Donnerstag 18.03. 09:45 - 11:15 Digital
  • Mittwoch 24.03. 09:45 - 11:15 Digital
  • Donnerstag 25.03. 09:45 - 11:15 Digital
  • Mittwoch 14.04. 09:45 - 11:15 Digital
  • Donnerstag 15.04. 09:45 - 11:15 Digital
  • Mittwoch 21.04. 09:45 - 11:15 Digital
  • Donnerstag 22.04. 09:45 - 11:15 Digital
  • Mittwoch 28.04. 09:45 - 11:15 Digital
    Hörsaal 2, Währinger Straße 29 2.OG
    Hörsaal 31 Hauptgebäude, 1.Stock, Stiege 9
  • Donnerstag 29.04. 09:45 - 11:15 Digital
  • Mittwoch 05.05. 09:45 - 11:15 Digital
    Hörsaal 2, Währinger Straße 29 2.OG
    Hörsaal 31 Hauptgebäude, 1.Stock, Stiege 9
  • Donnerstag 06.05. 09:45 - 11:15 Digital
  • Mittwoch 12.05. 09:45 - 11:15 Digital
  • Mittwoch 19.05. 09:45 - 11:15 Digital
  • Donnerstag 20.05. 09:45 - 11:15 Digital
  • Mittwoch 26.05. 09:45 - 11:15 Digital
  • Donnerstag 27.05. 09:45 - 11:15 Digital
  • Mittwoch 02.06. 09:45 - 11:15 Digital
  • Mittwoch 09.06. 09:45 - 11:15 Digital
  • Donnerstag 10.06. 09:45 - 11:15 Digital
  • Mittwoch 16.06. 09:45 - 11:15 Digital
  • Donnerstag 17.06. 09:45 - 11:15 Digital
  • Mittwoch 23.06. 09:45 - 11:15 Digital
    Hörsaal 2, Währinger Straße 29 2.OG
    Hörsaal 31 Hauptgebäude, 1.Stock, Stiege 9
  • Donnerstag 24.06. 09:45 - 11:15 Digital
  • Mittwoch 30.06. 09:45 - 11:15 Digital
    Hörsaal 2, Währinger Straße 29 2.OG
    Hörsaal 31 Hauptgebäude, 1.Stock, Stiege 9

Information

Ziele, Inhalte und Methode der Lehrveranstaltung

Today's currency is data. However, data is only useful if we are able to extract useful information from it. This is the aim of data analysis in general. This course aims to survey the foundations of data analysis. This includes concepts from statistical inference, regression analysis, classification analysis, clustering analysis, dimensionality reduction.

Concepts as well as techniques are introduced and practiced.

Due to the ongoing pandemic, we will adopt a mixed lecture format that complements pre-recorded video lectures with live (offline or online) review sessions. Details will be announced on Moodle.

Art der Leistungskontrolle und erlaubte Hilfsmittel

- 2 labs (i.e. programming exercises including peer review), for each lab you will get a maximum of 18% of the required points.

- 2 pen-and-paper exercise sheets. They serve as a preparation for the exams. For each exercise sheet you will be able to get a maximum of 5% of the required points.

- 2 exams, one mid-term and one final, each 25% of the total points.

Furthermore you can complete:

- 1 exercise sheet to assess your current mathematical (prerequisite) knowledge, 1% of the total points.

- 3 anonymized feedbacks, each 1% of the total points.

- in addition you can earn at most 10% of bonus points for completing voluntary quizzes

Mindestanforderungen und Beurteilungsmaßstab

For bachelor students, the mandatory prerequisite for this class is the successful completion of the following courses:
- StEOP
- Programmierung 2 (PR2)
- Mathematische Grundlagen der Informatik 2 (MG2)
- Theoretische Informatik (THI)
- Modellierung (MOD)
- Algorithmen und Datenstrukturen (ADS)

Grading will be done according to the following scheme:
1 – at least 87.5%
2 – at least 75.0%
3 - at least 60.0%
4 – at least 40.0%

Please keep in mind that in order to pass the course, you will need at least 30% of the total score in all labs and homeworks combined with 40% of the total score of the tests.

In order to successfully pass the course, regular attendance is strongly recommended, however not mandatory.

Prüfungsstoff

1. Models, Statistical Inference, and General Techniques
1.1. Fundamental Concepts in Inference
1.2. Parametric Inference
1.3. Hypothesis Testing and p-values
1.4. The Bootstrap
1.5. Data Splitting, Cross-Validation
2. Regression Modelling
2.1. Simple Linear Regression
2.2. Multiple Regression
2.3. Further Regression Methods
2.4. Generalized Linear Models
2.5. Regression Trees
3. Classification Modelling
3.1. Decision Theoretic Introduction; Error rates, and Bayes Optimality
3.2. Logistic Regression
3.3. Classification Trees
3.4. Support Vector Machines
3.6. Further Classification Methods
4. Neural Networks
5. Basic Techniques of Unsupervised Learning
5.1. Dimension Reduction (Matrix Factorization)
5.2. Association Rules
6. Clustering Methods
6.1. Hierarchical Clustering
6.2. Model-based Clustering
6.3. Evaluation and Validation of Clustering Results
6.4. Density-based Clustering
6.5. Self Organizing Maps

Literatur

> Christopher M. Bishop, Pattern Recognition and Machine Learning, Springer 2007.
> Han, Kamber: Data Mining: Concepts and Techniques, Elsevier 2012.
> Hastie-Tibshirani-Friedman: The Elements of Statistical Learning, Springer 2009.
> James-Witten-Hastie-Tibshirani: An Introduction to Statistical Learning with Applications in R, Springer 2015.

Zuordnung im Vorlesungsverzeichnis

Module: FDA AKM SWI STW

Letzte Änderung: Fr 12.05.2023 00:13