AWS On Air ft. Amazon SageMaker Canvas
summary
Amazon launches Amazon SageMaker Canvas, a no-code drag-and-drop UI that connects to S3, Redshift, Snowflake or local CSVs, auto-cleans data, does feature engineering and scaling, lets users join tables, preview feature importances and directionality, and run a quick build in minutes or a full build in hours. Models export with a couple clicks to export to SageMaker Studio for notebook tuning, and collaborative share links move results into production workflows while flagging high-missing or high-cardinality issues.
AI-written summary · about
chapters (15)
- 0:00Welcome and introduction
- 1:13Democratizing machine learning
- 4:03ETL and data preparation
- 6:08No-code UI benefits
- 8:15SageMaker ecosystem integration
- 9:37Product demo overview
- 12:03Data connections and joins
- 13:27Data analysis and visualization
- 14:49Data quality checks
- 15:35Model building options
- 16:58Preview model insights
- 17:41Feature importance discovery
- 18:23Advanced analytics progression
- 19:05Collaboration features
- 20:06How to get started
related talks
29mBuilding with Amazon SageMaker Unified Studio
44mExploratory data analysis and automated feature engineering
49mUse Amazon SageMaker to build high-quality ML models faster
31mUse AutoML to create high-quality models with just a few clicks
32mBuild, Train, and Deploy Machine Learning Models on AWS
33mAccelerate data preparation with Amazon SageMaker Data Wrangler
34mBuild, train and deploy Machine Learning models with Amazon SageMaker
58mPrepare data and model features for ML with ease, speed, and accuracy