GRADUATE COURSE · DAS410116

Generative Artificial Intelligence

Theory and practice of generative models, with emphasis on deep learning, Transformers, and Generative Adversarial Networks.

Graduate Program in Automation and Systems Engineering2 credits4 class hours per weekTwo-month coursePrerequisite: DAS410058 · Machine Learning

Syllabus

Deep learning. Generative AI. Transformers and Generative Adversarial Nets.

Learning objectives

This course introduces the principles of generative artificial intelligence and the deep learning concepts underlying modern generative models. It emphasizes the core principles and architectures of Transformers and Generative Adversarial Networks (GANs), combined with assignments, a seminar, and a project.

Course topics

The following modules are derived from the teaching plan, without semester-specific dates:

  1. Deep learning foundations
  2. Transformers I — introduction
  3. Transformers II — models and architectures
  4. Transformers III — extended concepts and applications
  5. Generative Adversarial Networks I
  6. Generative Adversarial Networks II
  7. Project and seminar development
  8. Seminar presentations
  9. Project presentations

Assessment model

40%Project
40%Seminar
20%Assignments and/or examination

A randomly selected group of students may be required to complete an oral examination to verify their understanding of the implementations submitted as assignments.

This is a reusable course overview rather than the timetable of a particular offering. Official assessment instructions and deadlines are published separately for each term.

References

  1. A. Zhang, Z. C. Lipton, M. Li, and A. J. Smola. Dive into Deep Learning. Cambridge University Press, 2023. Free online edition.
  2. I. Goodfellow, Y. Bengio, and A. Courville. Deep Learning. MIT Press, 2016. Free online edition.

← All courses · Machine Learning →