VVZ API is not affiliated with ETH Zurich. Data might be outdated or incorrect. Please view the official ETHZ Vorlesungsverzeichnis for binding information.
Deep Generative Models
Last Updated: 2026-06-01 11:33:22
Abstract
This course offers an in-depth exploration of deep generative models, focusing on foundational concepts, practical implementation, and the latest advancements in the field. Students will learn about key models such as Variational Autoencoders (VAEs), Generative Adversarial Networks (GANs), and diffusion models, gaining both theoretical knowledge and hands-on experience.
Objective
By engaging with real-world applications and cutting-edge research, students will develop a comprehensive understanding of the capabilities and limitations of deep generative models. By the end of this course, students will have developed a solid understanding of the core principles and theoretical underpinnings of deep generative models. They will be able to implement and train different types of generative models, evaluate their performance, and critically analyze their strengths and limitations. Students will also learn to apply these models to practical, real-world problems, demonstrating their ability to innovate and think creatively. Furthermore, the course aims to keep students informed about the latest trends and research in the field, enabling them to stay current and contribute meaningfully to advancements in deep generative modeling.
Content
The course content covers a wide range of topics related to deep generative models. It begins with the theoretical foundations of generative modeling, including detailed examinations of VAEs, GANs, diffusion models, and normalizing flows. Students will explore the objective functions, training procedures, and data generation capabilities of these models. The course also touches upon practical aspects including implementing and training these models using popular deep learning frameworks like TensorFlow and PyTorch. Additionally, students will work on projects and assignments that apply these models to various domains such as image generation and natural language processing
General Information
- Language
- English
- Levels
- MSC
- Frequency
- Yearly recurring
Examination
- Type
- session examination
- Mode
- written 90 minutes
- Aids
- None
Course Components
| Type | Title | Time & Place | Hours |
|---|---|---|---|
| lecture | Deep Generative Models |
|
2 h weekly |
Offered In
-
-
-
Vertiefung: Signal Processing and Machine Learning (The core courses and specialization courses below are a selection for students who wish to specialize in the area of "Signal Processing and Machine Learning ", see . The individual study plan is subject to the tutor's approval.)
-
Vertiefungsfächer (These specialization courses are particularly recommended for the area of "Signal Processing and Machine Learning", but you are free to choose courses from any other field in agreement with your tutor. Semester / Research Projects are not allowed in this category. A minimum of 40 credits must be obtained from specialization courses during the MSc EEIT.)
-
-
-
-
Fächer der Vertiefung (A total of 42 CP must be achieved form courses during the Master Program. The individual study plan is subject to the tutor's approval. Semester / Research Projects are not allowed in this category.)
-
-
-