- Docente: Fabio Genz
- Docente: Dieter Kranzlmüller
- Docente: Jan Schmidt
- Docente: Michael Windmann
Course instructor: Simon Rittel
Target group: Master Data Science with specialization track Machine Learning
Module: P 9 Current Research in Data Science
Course Description:
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.
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.
Students
will give two short talks and conclude their scientific investigation
with a seminar thesis on the assigned research paper.
- Docente: Simon Rittel
- Docente: Göran Kauermann
- Docente: Michael Windmann