Mathematical Foundations of Generative AI

Overview

ABOUT THE COURSE:

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 IndustryPREREQUISITES:

Probability, Course in Machine LearningINDUSTRY SUPPORT:

All ML Companies

Syllabus

• **Introduction to Generative AI**
• Overview of Generative Models
• Applications and Impact
• **Probabilistic Foundations**
• Basics of Probability Distributions
• Bayesian Inference
• Maximum Likelihood Estimation
• **Variational Autoencoders (VAEs)**
• Introduction to VAEs
• Variational Inference
• Implementation of VAEs in PyTorch
• **Generative Adversarial Networks (GANs)**
• Introduction to GANs
• Training Challenges and Solutions
• Implementation of GANs in PyTorch
• **Autoregressive Models**
• Overview and Examples (e.g., PixelRNN, PixelCNN)
• Likelihood-based Training
• Implementation in PyTorch
• **Diffusion Models**
• Introduction to Diffusion Models
• Sampling and Denoising Methods
• Practical Implementation
• **Large Language Models**
• Basic Concepts and Architectures
• Transformer Networks
• Training Large Language Models
• **Hands-On Practical Sessions**
• PyTorch Tutorials and Exercises
• Implementations of Deep Generative Models
• **Advanced Topics and Applications**
• Exploration of Cutting-edge Research
• Applications in Various AI Tasks
• **Assignments and Projects**
• Practical Implementations
• Capstone Project on a Generative AI Task
• **Review and Future Directions**
• Summary of Key Concepts
• Current Trends and Future of Generative AI

---

Taught by

Prof. Prathosh A P

---

Subjects

Artificial Intelligence