Applications Open now for May 2025 Batch | Applications Close: May 20, 2025 | Exam: July 13, 2025

Applications Open now for May 2025 Batch | Applications Close: May 20, 2025 | Exam: July 13, 2025

Degree Level Course

Generative AI

This course provides an in-depth exploration of deep generative models, including their probabilistic foundations and learning algorithms. Students will learn about various types of deep generative models such as variational autoencoders, generative adversarial networks, autoregressive models, Diffusion Models and Large Language Models. The course will cover both theoretical foundations and practical implementations of these models using popular frameworks like PyTorch. Students will gain hands-on experience through lectures and assignments, allowing them to explore deep generative models across various AI tasks.

by Prathosh A P

Course ID: BSDA5002

Course Credits: 4

Course Type:

Pre-requisites: None

What you’ll learn

Develop a deep understanding of the importance of generative models in artificial intelligence and machine learning.
Design and implement generative models using popular frameworks.
Implement a range of generative models, including autoregressive models, VAEs, GANs and Diffusion Models
Build problem-solving skills by tackling challenges and complexities in the practical implementation of generative models.

Course structure & Assessments

For details of standard course structure and assessments, visit Academics page.

WEEK 1 Introduction to Probabilistic Deep Generative Modelling
WEEK 2 Generative Modelling via variational Divergence Minimization
WEEK 3 Generative Adversarial Networks: Part 1 (Introduction and Formulation)
WEEK 4 Generative Adversarial Networks: Part 2 (WGANs and Applications)
WEEK 5 Generative Modelling via Variational Auto Encoding
WEEK 6 Variational Auto Encoders: Improvisations and VQVAE
WEEK 7 Denoising Diffusion Probabilistic Models (DDPMs) - Formulation
WEEK 8 Diffusion Models: Multiple forms and Implementation
WEEK 9 Conditional Diffusion Models and Score-based models
WEEK 10 Auto-Regressive Models and Large Language Models Introduction
WEEK 11 LLMs: Models, Sampling, Inference and Quantization Methods
WEEK 12 LLMs – Reinforcement Learning based Alignment Methods (PPO, DPO)
+ Show all weeks

Prescribed Books

The following are the suggested books for the course:

Foster D. Generative deep learning. " O'Reilly Media, Inc.; 2023

Recent papers/surveys that are relevant to the course.

About the Instructors

Prathosh A P
Assistant Professor, Division of EECS, IISc Bangalore