Generative AI: Concepts, Tools, and Applications for Data Professionals
summary
A practical tour of how generative models get built and used: history to LLMs, RAG (retrieval-augmented generation) for making models use private docs, and hands-on Azure tooling like Azure AI Studio and SQL Server Machine Learning Services. Demos include generating 2,000 ad letters for 4¢ from AdventureWorks data, calling DALL·E for images, and using GitHub Copilot for context‑sensitive code. Claims: GPT‑4 is GA, GPUs drive training (vendor chips cost ≈$40k each), and customer training data remains private and not reused for model improvement.
AI-written summary · about
chapters (7)
- 0:00Generative AI intro
- 1:52AI to generative AI
- 13:50Deep learning basics
- 18:27Natural language processing and transformers
- 27:00LLMs and foundation models
- 37:56AI in data workflows
- 46:51Responsible AI and job impact
related talks
01h 10mPractical Applications of Generative AI: How to Sprinkle a Little AI in Your App
17mGenerative AI: Keeping it real
35mGenerative AI in the real world
42mFrom theory to practice: The rise of Generative AI
15mPractical Evolution of Data Science with GenAI
15mHarnessing the Power of Generative AI for Intelligent Applications
19mLet's Talk GenAI
32mHow generative AI is Changing the way people interact with computers