Generative AI with Certification

Foundations of AI and ML: Difference between discriminative vs
generative models
Introduction to key Generative AI models
The evolution from GPT-2 to GPT-4 / GPT-4o and beyond
How GenAI models are trained, evaluated, and deployed
Understanding ethical, legal, and societal implications (bias,
misinformation, hallucinations)

LLMs (Large Language Models): Architecture overview
(Transformers), Pretraining vs Fine-tuning, RLHF, Inference
Embeddings: Vector representations, semantic similarity, use in
search, recommendation, and RAG.
Prompt Engineering: Role prompting, chain-of-thought, few-shot
prompting, constraint-based prompting
Prompt testing, evaluation metrics, and iterative refinement
Fine-Tuning: When to fine-tune vs use APIs
Tools: Hugging Face, LangChain, OpenAI API

Selecting a base model (GPT, Claude, open-source alternatives)
Designing conversation flow and behavior using prompt chaining
Integrating memory, tools (search, calculators), and APIs
Adding an open source UI to different models

Shift from LLMs to multi-modal AI (text, image, video, code)
Role of agents and tool-use
Open-source vs proprietary ecosystems
Compliance, safety layers, and trust-building in enterprise GenAI
Emerging roles: AI product managers, prompt engineers, AI
ethics leads

Introduction to VAEs

Understanding Autoencoders and Variational Autoencoders

Mathematical Foundations of VAEs

Applications of VAEs in Image Generation and Data Imputation

Hands-on Project: Building and Training a VAE