Microsoft · AI-901
Vision, image generation and information extraction
AI-901 · Lesson 4 of 10 · 21:34
YouTube loads only after you press play. This chapter opens at its timestamp in the full course. Watch on YouTube ↗
In this lesson
Prepare for the AI-901 exam (Microsoft Azure AI Fundamentals). In this lesson: computer vision tasks (image classification, object detection, semantic segmentation), captions vs OCR and multimodal models, how vision models work, image generation with diffusion (GPT-image family, FLUX) and video generation, and information extraction from documents, images, audio and video with Azure Content Understanding in Foundry Tools, compared with Azure Document Intelligence. Includes three original practice questions.
Preview the topics
- A self-checkout camera must find every product on the counter and draw a rectangle around each one. Which technique is this?
- Which statement best describes how most image generation models create a picture from a prompt?
- An insurer wants one service that applies the same field schema to scanned claim forms, recorded phone calls and dash-cam videos. Which service fits?