Module 1: Introduction to Generative AI
- Overview of Generative AI
- Types of Generative Models
- Ethical Considerations in Generative AI
Module 2: Mathematics and Foundations for Generative AI
- Linear Algebra
- Probability and Statistics
- Optimization Techniques
- KL Divergence and Information Theory
Module 3: Neural Network Foundations
- Basic Concepts of Neural Networks
- Training and Regularization
- Loss Functions in Deep Learning
Module 4: Variational Autoencoders (VAEs)
- Introduction to VAEs
- Mathematics Behind VAEs
- Applications of VAEs
Module 5: Generative Adversarial Networks (GANs)
- Introduction to GANs
- Types of GANs
- Applications of GANs
- Advanced GAN Topics
Module 6: Transformers and Large Language Models (LLMs)
- Introduction to Transformer Models
- Pretraining and Fine-Tuning
- Transformers in NLP
- Scaling Up: GPT Models
Module 7: Diffusion Models
- Introduction to Diffusion Models
- Mathematics Behind Diffusion Models
- Applications of Diffusion Models
Module 8: Retrieval-Augmented Generation (RAG)
- Introduction to RAG
- Building a RAG System
- Fine-Tuning RAG Models
- Optimizing and Scaling RAG Systems
Module 9: Multi-Modal Generative AI
- Introduction to Multi-Modal AI
- Training Multi-Modal Models
- Applications of Multi-Modal AI
Module 10: Fine-Tuning, Deployment, and Ethics
- Fine-Tuning Pretrained Generative Models
- Deployment of Generative AI Models
- Ethical Considerations
Module 11: Capstone Project and Review
- Capstone Project: End-to-End Generative AI Solution
- Project Presentation and Discussion
- Revision and Recap of Key Concepts