Applied AI: Real-world use cases for Microsoft's Azure Cognitive Services
summary
Shows a concrete Jabil circuit-board pipeline: use Project Pendleton for automated data cleaning, train on a deep learning VM with GPU via the Azure Machine Learning Workbench and Jupyter notebooks, track accuracy over time, then package the best model as a Docker web service that classifies pass/fail images in real factory UIs. Demonstrates Cognitive Services for face, vision, speech and translation as single REST API call building features like smile-to-unlock and real-time face feature mapping; ML Studio and Excel integrations are also runnable, free-tier friendly.
AI-written summary · about
chapters (7)
- 0:00Introduction to Azure Cognitive Services
- 3:19Jabil circuit board inspection case study
- 10:54Data science workflow with Azure tools
- 17:21Jupyter Notebooks hosting on Azure
- 23:27Simpler AI options beyond data science
- 26:18Azure Cognitive Services demos
- 30:57Resources and next steps
related talks
24mDon't want to miss out on the AI wave?
31mAzure AI Innovations at Microsoft
50mCognitive Services Extravaganza!
01h 01mAI and ML imbedded in Azure Data Platform
01h 00mLearn Live: Get started with AI on Azure
01h 05mMicrosoft Cognitive Services: Making AI Easy
44mThe age of applied AI
01h 00m5 Levels of AI in Microsoft Azure