Universität Wien

136308 UE (A)I Want It Data Way: Cracking the (Python) Code of Time Series Analysis with LLMs (2024W)

5.00 ECTS (2.00 SWS), SPL 13 - Europäische und Vergleichende Sprach- und Literaturwissenschaft
Continuous assessment of course work
Moodle
Tu 08.10. 11:30-14:45 Ort in u:find Details

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).
Register/Deregister for this course

Details

max. 12 participants
Language: German

Lecturers

Classes (iCal) - next class is marked with N

Location: PC-Schulungsraum 2H363, Stiege H, Ebene 3, Rotunde, UZA 2, Josef-Holaubek Platz 2, 1090 Wien
https://medialab.univie.ac.at/anfahrt

Attention: Due to the special nature of the room, the number of participants in this exercise course is limited to 12 people.

  • Tuesday 22.10. 11:30 - 14:45 Ort in u:find Details
  • Tuesday 05.11. 11:30 - 14:45 Ort in u:find Details
  • Tuesday 19.11. 11:30 - 14:45 Ort in u:find Details
  • Tuesday 03.12. 11:30 - 14:45 Ort in u:find Details
  • Tuesday 07.01. 11:30 - 14:45 Ort in u:find Details
  • Tuesday 21.01. 11:30 - 14:45 Ort in u:find Details

Information

Aims, contents and method of the course

Get ready to dive into the exciting world of time series analysis using Python, powered by the magic of Large Language Models (LLMs) like ChatGPT! In this hands-on course, you'll explore the fascinating realm of motion capture data and learn how to apply various analytical methods to uncover hidden patterns and insights.

Here's what you'll do:
Learn by Doing: Whether you're a coding newbie or a Python pro, this course is designed for everyone. With the help of LLMs, you'll quickly pick up the skills to write, understand, and apply Python code.
Define Your Quest: You'll define your own research questions and embark on a project that captures your imagination. Think big, think bold - the more creative and quirky, the better!
Continuous Adventure: As you progress, you'll document your journey, share your findings, and engage in lively discussions with your peers.
Chase the Bizarre Prize: To add a sprinkle of fun, the most bizarre and unique project will win a special prize, judged by an LLM in a whimsical dystopian twist (don't worry, this won't affect your grade).

What You'll Learn:
Time series analysis techniques and their applications
Writing and debugging Python code with LLM assistance
Selecting and applying appropriate analytical methods to answer your research questions
Documenting and presenting your project findings effectively

Assessment and permitted materials

The following partial performances serve as performance control and will be evaluated at the end of the semester. Feedback will also be provided during the semester.

Active participation and contributions in discussions (10 points).
Comprehensive project documentation including a report (30 points).
Appropriateness of the chosen analytical methods (20 points).
Clarity and functionality of the Python code (20 points).
Engaging and informative project presentation (20 points).

Performances must be submitted on time via Moodle. Please note the attendance requirement for the course. A maximum of one unexcused absence (each 2 x 90 minutes) is allowed.

All used resources must be disclosed in advance, and their usage must be appropriately indicated.

Minimum requirements and assessment criteria

Active participation and contributions in discussions (10 points)
Comprehensive project documentation (30 Points)
Appropriateness of the analysis methods chosen ( 20Points)
Clarity and functionality of your Python code (20 Points)
Engaging and informative project presentation (20 Points)

At least 50% of the maximum achievable points are required for a passing grade. Additionally, every partial performance must be completed.

Examination topics

All course contents are relevant for the project work. There is no written or oral exam.

Reading list

Will be provided on Moodle.

Association in the course directory

DH-S II
Cluster I
Cluster III
Cluster IV

Last modified: Fr 06.09.2024 06:45