Basics of Generative AI and its evolution. Generative vs. Discriminative Models. Foundations of Deep Learning: Neural Networks, Backpropagation, and Activation Functions. Introduction to Key Architectures: Diffusion Models, Transformers, and Large Language Model (LLM) Architecture Overview. Critical Examination of Ethics, Risks, and Hallucination in AI Systems. Lab Practice 1. Working with a basic text generation model (e.g., using the transformers library with GPT-2). 2. Generating simple outputs (text, code) using an open-source GenAI tool (e.g., Ollama with a small LLM).

Language Model Families: GPT-series, LLaMA, Gemini. Vision Foundation Models: Stable Diffusion, Midjourney, DALL•E. Core Preprocessing: Tokenization and Embeddings. Introduction to Fine-tuning and Efficient Adaptation Methods: LoRA (Low-Rank Adaptation) and QLoRA. Lab Practice 1. Advanced text generation and conversation using a hosted or local LLM (e.g., using OpenAI API or Hugging Face Chat). 2. Image generation and manipulation using a diffusion model (e.g., Stable Diffusion via Automatic1111 or ComfyUI).

Generative Painting and Illustration Models (e.g., Midjourney, Stable Diffusion for art). Music Generation Models: MuseNet, MusicLM. Script and Play Generation using LLMs. Introduction to Multimodal AI Models (e.g., GPT-4V). Overview of Creative AI Applications in various industries Lab Practice 1. Creating AI-generated painting/illustration based on a detailed thematic prompt. 2. Music composition using AI tools (e.g., MusicGen) or script generation for a short play.

Types of Prompts: Zero-Shot, Few-Shot, Chain-of-Thought (CoT). System Prompts and Role Prompting for controlling model behavior. Techniques for Prompt Optimization and Evaluation. Safety, Bias Mitigation, and Alignment Prompting Lab Practice 1. Building and iterating complex prompts for specific text generation tasks (summarization, creative writing, code generation). 2. Designing prompts for multimodal tasks (e.g., generating an image with a specific style and then having an LLM describe it).

Concept of Autonomous AI Agents. Core Components: Tool Use, Memory, and Planning. Introduction to Multi-Agent Systems. Agent Frameworks: LangChain Agents, AutoGen. Real-world Use Cases and Applications of Agentic AI. Lab Practice 1. Building a simple AI agent that can perform a multi-step task (e.g., web search and summarization). 2. Integrating an AI agent with external tools or APIs (e.g., a calculator, database, or web search).