Course instructor: Simon Rittel
Target group: Master Data Science
The research paper by Kingma and Welling (2014) introducing Variational Autoencoder (VAE) received the ''ICLR 2024 Test of Time Award'' for its seminal impact on the research on probabilistic models and encoding of latent representations.
VAEs provide a gentle introduction to the steadily growing world of deep generative models with low entry barriers, e.g. computational power or complexity, particularly suitable for Master's students who are new to probabilistic machine learning.
This seminar covers various extensions of the VAE framework offering a broader overview of the research area and shedding light on its individual components and characteristics. The more general techniques for probabilistic models used in the context of VAEs allow to draw connections to related subfields.
- Викладач: Bothmann Ludwig
- Викладач: Rittel Simon
In the last decade, the availability of huge data repositories and the
strong increase in computational powers have empowered artificial
intelligence techniques like neural networks and reinforcement learning.
Big Data became the synonym for large, heterogeneous, and dynamic data
sources. However, challenges like data quality and non-iid data sources
have become more pressing with the new wealth of data.
The course
provides an introduction to deep neural
networks, which exploit these new conditions to extend the capabilities
of Artificial Intelligence Systems constantly. In addition, it
covers techniques for handling Big Data sources using modern Hardware
like Compute Clouds and GPU-Computing like NoSQL databases and Batch
Systems
Note: This course is aimed exclusively at students of the elite master's program Data Science and part of a module spanning two semesters with a consolidated oral exam at the end. That is if you are not enrolled in the Data Science program, you can unfortunately not take this course.
- Викладач: Pfefferkorn Philipp
- Викладач: Schubert Matthias
The seminar on Data Ethics is part of the MSc Data Science program at Ludwig-Maximilians-Universität (LMU) Munich. The course will be lead by Prof. Dr. Dieter Kranzlmüller and Fabio Genz.
Contents: The seminar is one part of the module Data Ethics and Data Security, which covers basic legal and ethical questions and challenges of data security. This course helps the students to prepare lectures on ethical and legal aspects of data ethics. Students are introduced to the technical, legal, and ethical issues of data security, especially when dealing with personal data or when planning experiments in Data Science.
Objective: Students will reflect on standard procedures and problems of data protection and learn technical methods to handle data responsibly.
- Викладач: Genz Fabio
- Викладач: Kranzlmüller Dieter
- Викладач: Windmann Michael