Universität Wien
Warning! The directory is not yet complete and will be amended until the beginning of the term.

053613 VU Introduction to Machine Learning (2020W)

6.00 ECTS (4.00 SWS), SPL 5 - Informatik und Wirtschaftsinformatik
Continuous assessment of course work
Moodle

Registration/Deregistration

Note: The time of your registration within the registration period has no effect on the allocation of places (no first come, first served).

Details

max. 25 participants
Language: English

Lecturers

Classes (iCal) - next class is marked with N

  • Friday 02.10. 13:15 - 14:45 Digital
  • Monday 05.10. 15:00 - 16:30 Digital
  • Friday 09.10. 13:15 - 14:45 Digital
  • Monday 12.10. 15:00 - 16:30 Digital
  • Friday 16.10. 13:15 - 14:45 Digital
  • Monday 19.10. 15:00 - 16:30 Digital
  • Friday 23.10. 13:15 - 14:45 Digital
  • Friday 30.10. 13:15 - 14:45 Digital
  • Friday 06.11. 13:15 - 14:45 Digital
  • Monday 09.11. 15:00 - 16:30 Digital
  • Friday 13.11. 13:15 - 14:45 Digital
  • Monday 16.11. 15:00 - 16:30 Digital
  • Friday 20.11. 13:15 - 14:45 Digital
  • Monday 23.11. 15:00 - 16:30 Digital
  • Friday 27.11. 13:15 - 14:45 Digital
  • Monday 30.11. 15:00 - 16:30 Digital
  • Friday 04.12. 13:15 - 14:45 Digital
  • Monday 07.12. 15:00 - 16:30 Digital
  • Friday 11.12. 13:15 - 14:45 Digital
  • Monday 14.12. 15:00 - 16:30 Digital
  • Friday 18.12. 13:15 - 14:45 Digital
  • Friday 08.01. 13:15 - 14:45 Digital
  • Monday 11.01. 15:00 - 16:30 Digital
  • Friday 15.01. 13:15 - 14:45 Digital
  • Monday 18.01. 15:00 - 16:30 Digital
  • Friday 22.01. 13:15 - 14:45 Digital
  • Monday 25.01. 15:00 - 16:30 Digital
  • Friday 29.01. 13:15 - 14:45 Digital

Information

Aims, contents and method of the course

Goals:
Upon successful participation in the course, students will understand the fundamentals of machine learning and how to apply basic machine learning approaches/ideas in theory and practice.

Lecture Contents:
* What is Machine Learning?
* Basic Machine Learning pipelines
* Linear models for regression
* Linear models for classification
* Model validation and model selection
* Kernels
* Neural networks
* Dimensionality reduction
* Probabilistic modeling
* Generative modeling
* Deep generative models

Method:
Lecture (recorded lectures will be made available via Moodle) + pen & paper exercises + programming exercises

Assessment and permitted materials

Written exam
Programming exercises

Minimum requirements and assessment criteria

50% Written exam
50% Programming exercises
Voluntary pen&paper exercises

P = Average percentage on the final written exam and the programming exercises

85% <= P <= % Sehr Gut (1)
74% <= P < 85% Gut (2)
62% <= P < 74% Befriedigend (3)
50% <= P < 62% Genügend (4)
0% <= P < 50% Nicht Genügend (5)

At least 50% on the final written exam and 50% on the programming exercises must be achieved for a passing grade.

Examination topics

The presented topics in the lecture (according to slides + exercises). Referenced Literature (as indicated in detail on lecture slides).

Reading list

* Christopher Bishop, 2006, "Pattern Recognition and Machine Learning", Springer; available online: https://www.microsoft.com/en-us/research/publication/pattern-recognition-machine-learning/
* Trevor Hastie, Robert Tibshirani, Jerome Friedman, 2009, "The Elements of Statistical Learning: Data Mining, Inference, and Prediction", Springer; available online: https://web.stanford.edu/~hastie/ElemStatLearn/
* Tom Mitchell, 1997, "Machine Learning", McGraw Hill
* Shai Shalev-Shwartz and Shai Ben-David, 2014, "Understanding Machine Learning: From Theory to Algorithms", Cambridge University Press; available online: https://www.cs.huji.ac.il/~shais/UnderstandingMachineLearning/

Association in the course directory

Last modified: Fr 12.05.2023 00:13