Back to teaching
Generative Networks
Explore the world of generative models, from GANs to Transformers and modern diffusion models. Learn how these networks can create new data samples and understand the mathematical foundations behind generative artificial intelligence.
Advanced Level
5 weeks
Undergraduate Course
Course Overview
This advanced course covers the theoretical foundations and practical applications of generative models in machine learning. Students will explore various architectures including Generative Adversarial Networks (GANs), Variational Autoencoders (VAEs), and modern diffusion models.
The course combines mathematical rigor with hands-on implementation, ensuring students understand both the theory behind these models and how to apply them to real-world problems in computer vision and natural language processing.
Learning Objectives
- •Understand the mathematical foundations of generative modeling
- •Apply generative models to image synthesis, text generation, and data augmentation
- •Evaluate and compare different generative approaches
- •Understand current research trends and future directions
Topics Covered
Foundations
- • Probability theory and statistics
- • Information theory basics
- • Maximum likelihood estimation
- • Variational inference
Models
- • Variational Autoencoders (VAEs)
- • Generative Adversarial Networks (GANs)
- • Normalizing Flows
- • Flow Matching
- • Transformers
- • Diffusion Models
Course Information
Duration: 5 weeks
Credits: 6 ECTS
Language: English/Spanish
Prerequisites: Machine Learning, Linear Algebra, Python