Leveraging Automated Machine Learning to enable anyone to develop Machine Learning solutions
summary
Claims that Azure Automated ML produces production-quality models with minimal expertise by running automated model selection plus feature engineering and hyperparameter tuning. Demo uses a bank customer dataset to predict Y/N subscription (a classification task), runs on a configurable Azure compute cluster (samples take ~30 minutes per run), emits metrics, data-guardrail checks and downloadable models, and can deploy as a web service or integrate via the Python SDK.
AI-written summary · about
chapters (10)
- 0:00Introduction and welcome
- 1:29What is Machine Learning
- 8:55Azure ML studio overview
- 14:15Challenges in ML development
- 14:36What is Automated ML
- 18:25Automated ML capabilities
- 23:26Benefits of Automated ML
- 24:10Demo Automated ML on Azure
- 34:23Summary and conclusion
- 36:06Q&A session
related talks
58mDeep Dive into Azure Automated Machine Learning
49mAutomated Machine Learning on Azure
01h 05mAzure Machine Learning for the Developer
43mA lap around Azure Machine Learning services
51mTaking Models to the Next Level with Azure Machine Learning
48mStreamlining your Machine Learning projects with Azure Machine Learning
57mTaking Models to the Next Level with Azure Machine Learning
49mEnhanced AML fraud detection solutions with Azure Machine Learning