Practicing Data Science in the cloud
summary
Shows an end-to-end pipeline using Azure Machine Learning Services with Jupyter notebooks to train a one‑class SVM on streamed Raspberry Pi sensor data, store raw events in Data Lake, and visualize via Stream Analytics and Power BI. Training runs are packaged as Docker, pushed to cloud compute targets (Data Science VM, GPU/batch options) and returned; the selected model is deployed to edge as an IoT Edge module that detects anomalies in real time and triggers alerts—demo completes successfully.
AI-written summary · about
chapters (17)
- 0:00Intro
- 1:28Data Science Process
- 3:47Modeling and Operations
- 12:15Data Science in the Cloud
- 14:42Machine Learning Pipeline
- 17:16Machine Learning Services
- 19:24Choosing an Environment
- 22:19Dashboard
- 22:57Python
- 25:09Training
- 26:04Making it work
- 27:24Training a neural network
- 28:54Changing parameters
- 29:19Machine learning workspace
- 31:19Compute targets
- 33:29Final remarks
- 34:59Question time
related talks
45mFrom Data to AI on The Edge
25mFrom Data Exploration to Modeling to Deployment
40mThe data scientists are gone. how do I deploy their work to prod?
48mStreamlining your Machine Learning projects with Azure Machine Learning
10mGet Started with Azure Machine Learning
43mA lap around Azure Machine Learning services
01h 01mStreams, lakes and oceans – working with on big data with Azure ML
48mMachine Learning in Azure Databricks