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

250047 VU Applied machine learning (2022W)

7.00 ECTS (4.00 SWS), SPL 25 - Mathematik
Continuous assessment of course work
ON-SITE
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. 50 participants
Language: German

Lecturers

Classes (iCal) - next class is marked with N

Vorbesprechung am 3. Oktober 16:45.

  • Monday 03.10. 16:45 - 18:15 Hörsaal 11 Oskar-Morgenstern-Platz 1 2.Stock
  • Wednesday 05.10. 16:45 - 18:15 Hörsaal 11 Oskar-Morgenstern-Platz 1 2.Stock
  • Monday 10.10. 16:45 - 18:15 Hörsaal 11 Oskar-Morgenstern-Platz 1 2.Stock
  • Wednesday 12.10. 16:45 - 18:15 Hörsaal 11 Oskar-Morgenstern-Platz 1 2.Stock
  • Monday 17.10. 16:45 - 18:15 Hörsaal 11 Oskar-Morgenstern-Platz 1 2.Stock
  • Wednesday 19.10. 16:45 - 18:15 Hörsaal 11 Oskar-Morgenstern-Platz 1 2.Stock
  • Monday 24.10. 16:45 - 18:15 Hörsaal 11 Oskar-Morgenstern-Platz 1 2.Stock
  • Monday 31.10. 16:45 - 18:15 Hörsaal 11 Oskar-Morgenstern-Platz 1 2.Stock
  • Monday 07.11. 16:45 - 18:15 Hörsaal 11 Oskar-Morgenstern-Platz 1 2.Stock
  • Wednesday 09.11. 16:45 - 18:15 Hörsaal 11 Oskar-Morgenstern-Platz 1 2.Stock
  • Monday 14.11. 16:45 - 18:15 Hörsaal 11 Oskar-Morgenstern-Platz 1 2.Stock
  • Wednesday 16.11. 16:45 - 18:15 Hörsaal 11 Oskar-Morgenstern-Platz 1 2.Stock
  • Monday 21.11. 16:45 - 18:15 Hörsaal 11 Oskar-Morgenstern-Platz 1 2.Stock
  • Wednesday 23.11. 16:45 - 18:15 Hörsaal 11 Oskar-Morgenstern-Platz 1 2.Stock
  • Monday 28.11. 16:45 - 18:15 Hörsaal 11 Oskar-Morgenstern-Platz 1 2.Stock
  • Wednesday 30.11. 16:45 - 18:15 Hörsaal 11 Oskar-Morgenstern-Platz 1 2.Stock
  • Monday 05.12. 16:45 - 18:15 Hörsaal 11 Oskar-Morgenstern-Platz 1 2.Stock
  • Wednesday 07.12. 16:45 - 18:15 Hörsaal 11 Oskar-Morgenstern-Platz 1 2.Stock
  • Monday 12.12. 16:45 - 18:15 Hörsaal 11 Oskar-Morgenstern-Platz 1 2.Stock
  • Wednesday 14.12. 16:45 - 18:15 Hörsaal 11 Oskar-Morgenstern-Platz 1 2.Stock
  • Monday 09.01. 16:45 - 18:15 Hörsaal 11 Oskar-Morgenstern-Platz 1 2.Stock
  • Wednesday 11.01. 16:45 - 18:15 Hörsaal 11 Oskar-Morgenstern-Platz 1 2.Stock
  • Monday 16.01. 16:45 - 18:15 Hörsaal 11 Oskar-Morgenstern-Platz 1 2.Stock
  • Wednesday 18.01. 16:45 - 18:15 Hörsaal 11 Oskar-Morgenstern-Platz 1 2.Stock
  • Monday 23.01. 16:45 - 18:15 Hörsaal 11 Oskar-Morgenstern-Platz 1 2.Stock
  • Wednesday 25.01. 16:45 - 18:15 Hörsaal 11 Oskar-Morgenstern-Platz 1 2.Stock
  • Monday 30.01. 16:45 - 18:15 Hörsaal 11 Oskar-Morgenstern-Platz 1 2.Stock

Information

Aims, contents and method of the course

Machine learning plays an essential role almost everywhere in technology and research these days. The creation of data-driven models, which can be used efficiently as proxy and/or prediction models for new data, requires "know-how" in the mathematical basics as well as experience in dealing with the appropriate software packages.
The VU aims to "reconcile" theoretical and application-relevant aspects. In addition to the particularly practically relevant basics such as data analysis, model selection, validation, over- and underfitting, "feature selection", we will discuss "classical methods" such as non-linear model reduction (PCA, MDS, kernel methods, etc.), classification (logistic regression, random forests , SVMs, etc), regression (kernel rigde regression, lasso, etc), clustering, ensemble learning, as well as the basics of the current Deep Neural Networks (DNN), especially new advanced methodologies like autoencoders/-decoders, convolutional Neural Networks and " Physics-Informed Neural Networks (PINN)".

Using practical exercises, the handling of this is taught "hands-on" via Python, scikit-learn and keras/tensor flow, where we use the no-setup environment Kaggle with free GPU access. The VU will also deal with current research topics and applications in physics and materials research.

Structure:
The VU "Applied Machine Learning" combines (i) a "theory part" where mathematical and numerical basics of machine learning are presented, (ii) practical exercises that accompany the first part, and (iii) a "group work" where a small application problem in groups of about 2-6 people is considered and presented.

Assessment and permitted materials

The grade results from the elaboration/tests and the team project.

Minimum requirements and assessment criteria

The course imparts basic knowledge about "Machine Learning" using lectures, exercises and a small team project.

Examination topics

Moodle test + presentation of team project in the end of semester

Reading list

Lecture notes.

Further literature:
Aurélien Géron, Hands-On Machine Learning with Scikit-Learn, Keras, and TensorFlow, 2nd Edition. O'Reilly Media, 2019.
Forsyth, David, Applied Machine Learning. Springer International Publishing, 2019.
Shalev-Shwartz, Shai, and Shai Ben-David, Understanding machine learning: From theory to algorithms. Cambridge university press, 2014.

Association in the course directory

ZWM

Last modified: Th 29.09.2022 16:49