Building ML practices to address the top four use cases
summary
Covers four concrete ML products and what they actually do: Amazon Personalize delivers real-time, per-user recommendations using hierarchical recurrent nets, an HRNN cold-start model and auto feature engineering (demo shows different product lists per user). Amazon Forecast runs ARIMA and deep RNN recipes (claims ~15% accuracy gains) to cut inventory days and enable one‑day shipping decisions. Computer vision uses SageMaker Ground Truth plus Recognition and Gluon CV toolkits; Textract returns key/value JSON, Transcribe supports 137 language pairs.
AI-written summary · about
chapters (7)
- 0:00Introduction and strategy
- 2:30The layered AI/ML approach
- 8:20Recommendation engines
- 17:06Business forecasting
- 26:15Computer vision applications
- 32:33Natural language processing
- 38:58Building your practice
related talks
01h 41mGetting started with Machine Learning on AWS.
22mReal-world applications of machine learning: Beyond the hype
30mBring AutoML to all users across your business
21mBuilding Scalable ML Systems: Strategies and Insights
42mSolving 3 business problems with ML.NET in 45 minutes
36mSolve common business problems with AI/ML
29mSolve common business problems with AI and ML
45mStart your AI/ML Projects Right