UNIT I

INTRODUCTION TO GENERATIVE AI

Basics of Generative AI ᎓ Evolution and key applications ᎓ GenAI in engineering, industry, and automation ᎓ Opportunities and challenges ᎓ Ethical considerations ᎓ Overview of LLMs, multimodal models, and agent concepts

UNIT II

NEURAL NETWORK FOUNDATIONS FOR GENERATION

Overview of neural networks ᎓ Autoencoders and Variational Autoencoders (VAEs) ᎓ Generative Adversarial Networks (GANs): architecture and intuition ᎓ Comparison of reconstructive and adversarial generation ᎓ Simple latent-space visualization

UNIT III

LARGE LANGUAGE MODELS (LLMs), RAG, AND MCP

Transformer fundamentals ᎓ BERT, GPT family ᎓ Prompt engineering ᎓ Basic fine-tuning concepts ᎓ Retrieval-Augmented Generation (RAG): embeddings, search, and context retrieval ᎓ Introduction to Model Context Protocol (MCP) for t**l use

UNIT IV

MULTIMODAL GENERATION AND AGENTIC AI

Sequence models: RNN, LSTM for generative tasks ᎓ Text᎓image generation᎓Introduction to AI Agents: planning loops, t**l invocation, RAG-enabled agents ᎓ Simple multimodal demo.

UNIT V

EXPLAINABLE AIAND APPLICATIONS

Explainability techniques (LIME, SHAP) ᎓ Fairness, Safety, Transparency ᎓ Responsible Deployment of Generative Systems ᎓ Hallucinationand error analysis in RAG/LLMs ᎓ Introduction to regulatory and ethical frameworks ᎓ Application of GenAI(PCB Design Optimization, Semiconductor Chip Architecture Generation, Code Generation for ECU) ᎓ Application of Agentic AI (Engineering Bill of Materials (BoM) Generation, Autonomous Design Assistance, Noise Removal in Signals)