Generative AI

Learn Generative AI from the fundamentals to advanced concepts including LLMs, Transformers, Prompt Engineering, RAG, Fine-Tuning, AI Agents, Multimodal AI, Security, and Deployment.

Start Learning17 sections207 topics

Unit 1: Introduction to Generative AI

What is Generative AIThe topic becomes useful when its purpose, inputs, processing steps, outputs, evaluation method and limitations are understood together.
AI vs ML vs Deep Learning vs Generative AIThe topic becomes useful when its purpose, inputs, processing steps, outputs, evaluation method and limitations are understood together.
Generative vs Discriminative ModelsThe topic becomes useful when its purpose, inputs, processing steps, outputs, evaluation method and limitations are understood together.
Applications of Generative AIAn AI application combines a user problem, data, model or retrieval layer, software logic, interface, evaluation and safeguards.
TextThe topic becomes useful when its purpose, inputs, processing steps, outputs, evaluation method and limitations are understood together.
ImageImage generation systems map a textual, visual or structural condition into a new image while balancing prompt adherence, visual quality and consistency.
AudioAudio AI works with signals that vary over time; systems may recognize speech, synthesize speech, transform voices, or generate music.
VideoVideo adds time to image generation, so a useful system must maintain appearance, motion and continuity across many frames.
CodeThe topic becomes useful when its purpose, inputs, processing steps, outputs, evaluation method and limitations are understood together.
Generative AI lifecycleThe topic becomes useful when its purpose, inputs, processing steps, outputs, evaluation method and limitations are understood together.
Challenges and limitationsThe topic becomes useful when its purpose, inputs, processing steps, outputs, evaluation method and limitations are understood together.
Ethics, bias, privacy and responsible AIResponsible AI requires the system to consider accuracy, fairness, privacy, misuse, access control, transparency, human oversight and the consequences of failure.

Unit 2: Machine Learning & Deep Learning Basics

Unit 3: Transformers & Attention

Unit 4: Large Language Models (LLMs)

Unit 5: Prompt Engineering

Unit 6: Generative AI Models

Unit 7: Generative AI for Images

Unit 8: Generative AI for Audio & Video

Unit 9: Embeddings & Vector Databases

Unit 10: RAG – Retrieval Augmented Generation

Unit 11: Fine-Tuning & Model Adaptation

Unit 12: AI Agents

Unit 13: Generative AI Development

Unit 14: Generative AI Applications

Unit 15: Security, Ethics & Responsible AI

Unit 16: Deployment & MLOps

Unit 17: Course Summary & Project Roadmap

Course Summary & Project RoadmapHow the full Generative AI stack fits together — RAG vs fine-tuning vs prompting vs agents, evaluation, a production security checklist, a staged project roadmap and a final revision checklist.