Generative AI for Data Compression and Transmission, 6 credits

Main field of study

Course level

Advancement level

Course offered for

• Master of Science in Applied Physics and Electrical Engineering
• Master's Programme in Data Science and Information Engineering

Prerequisites

Calculus (e.g., differentiation and integration), linear algebra (e.g., matrix operations), and probability (e.g., random variables, central limit theorem) • A first course in machine learning, e.g., Machine Learning • Python programming skills, e.g., to train a machine learning model

Intended learning outcomes

After completing the course, the student should be able to: 

1. explain theoretical foundations of deep generative modeling, including methods for modeling a density function, network structure, loss function, and training routines; 
2. implement and train generative AI models to generate new data, and apply these models in a data compression and transmission system; 
3. analyze and evaluate the effectiveness of a solution based on generative modeling for data compression and transmission; 
4. reflect on implications and ethical considerations of using generative AI tools

Outcomes 1, 3, and 4 are fostered by the lectures and tutorieals, and assessed via the written examination. Outcomes 2 and 3 are fostered by lab sessions, and assessed via the lab reports. Outcome 4 is further fostered by peer assessment

Course content

This course provides an introduction to generative models, their applications to data compression and transmission, and their implications and ethical considerations. This includes: introduction to probabilistic generative modeling; generative models (including variational autoencoders, generative adversarial networks, diffusion models, flow-based models, energy-based models, transformers); frameworks and techniques for generative-AI-based data compression and transmission, including neural compression, rate-distortion-perception tradeoff, latent coding, joint source-channel coding; privacy, security, and ethical considerations of generative AI.

Examination

Grades

Department

Course literature

Books

• Tomczak, Jakub M, (2024) Deep generative modeling. 2nd ed. Cham : Springer, 2024.
  ISBN: 9783031640872, 303164087X

Articles

• Blau, Yochai, Michaeli, Tomer, Rethinking Lossy Compression: The Rate-Distortion-Perception Tradeoff ICML pp. 675-685, 2019
• Bourtsoulatze, E., Burth Kurka, D., Gunduz, D., Deep Joint Source-Channel Coding for Wireless Image Transmission IEEE Transactions on Cognitive Communications and Networking vol. 5, no. 3, pp. 567-579, Sept. 2019.
• Dai, Jincheng, Qin, Xiaoqi, Wang, Sixian, Xu, Lexi, Niu, Kai, Zhang, Ping, Deep Generative Modeling Reshapes Compression and Transmission: From Efficiency to Resiliency IEEE Wireless Communications vol. 31, no. 4, pp. 48-56, August 2024
• Yibo Yang, Stephan Mandt and Lucas Theis, An Introduction to Neural Data Compression Foundations and Trends in Computer Graphics and Vision Vol. 15: No. 2, pp 113-200. 2023