Course10610800444 lectures
Mathematical Foundations of Generative AI
Prof. Prathosh A. P · IISc Bangalore
About
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.
Intended audience: Academics and Industry
Prerequisites: Probability, Course in Machine Learning
Lectures
Week 1 Introduction
Week 2 Generative Models : Problem Formulation
- Generative Models : Problem Formulation
- Tutorial 3 : PyTorch Basics
- Tutorial 4 : CNNs using PyTorch
- Tutorial 5 : RNNs using PyTorch
- Tutorial 6 : Transfer Learning with PyTorch
Week 3 Review of Probability and Machine Learning
- Tutorial 7 : Review of Basic Probability 1
- Tutorial 8 : Review of Basic Probability 2
- Tutorial 9 : Review of Basic Probability 3
- Tutorial 10 : Review of Machine Learning 1
Week 4 f- Divergence
Week 5 GANs
- Variational Divergence Minimization (VDM)
- Generative Adversarial Networks (GANs)
- Tutorial 12 : Implementations of Vanilla GAN, DCGAN and Conditional GAN
Week 6 GANs and VAEs
- Wasserstein GAN (WGAN)
- Inversion with GANs and FID
- Latent Variable Models and Introduction to Variational Autoencoder (VAE)
Week 7 VAEs
Week 8 Diffussion Models
- Diffussion Models - Part 1
- Diffussion Models - Part 2
- Tutorial 13 : Wasserstein GAN (WGAN) Implementation using Gradient Clip
- Tutorial 14 : Wasserstein GAN (WGAN) Implementation using Gradient Penalty
- Tutorial 15 : VAE and Beta-VAE Implementation
Week 9 Diffusion Models contd.
- Pedagogy in the Times of AI
- Diffussion Models - Part 3
- Diffussion Models - Part 4
- Tutorial 16 : Implementation of VQ-VAE
- Tutorial 17 : Implementation overview of Diffusion Models
Week 10 Flow Matching Models
- Flow Matching Part 1
- Flow Matching Part 2
- Tutorial 18: Implementation of Diffussion Models Part 1
- Tutorial 19: Implementation of Diffussion Models Part 2
Week 11 Flow Matching and AR Models
Week 12 RLHF
Syllabus and materials
At NPTEL, as the course publishes them.
Credits and licence
- Institution
- IISc Bangalore
- Department
- Computer Science and Engineering
- Teacher
- Prof. Prathosh A. P
- Level
- Undergraduate
- Language
- English
- Subjects
- Computer science, Engineering
- Source
- NPTEL
- Licence
- CC BY-NC-SA, as NPTEL states it. Non-commercial use only. NPTEL's terms
- Attribution
- NPTEL states: "Distributed under Creative Commons Attribution-ShareAlike / CC BY - NC - SA", beside a BY-NC-SA badge.
- Who can watch
- NPTEL gives no rating. Invisible Network shows it to Tweens profiles and older, judged from what the source says about it. How courses are placed