Use AutoML to Create High-Quality Models
summary
Claims that AutoGluon plus Amazon SageMaker workflows build competitive models with three lines of code, stacking diverse learners and transformers, and often one or two ensemble layers. Benchmarks show first/second places and reproduceable results achieved in about four hours versus months of hand-tuning. Features listed include multimodal support (images, text, tabular), Hugging Face and CLIP integration, teacher–student distillation, adaptive early stopping, inference-latency limits, and deployable containers via SageMaker Autopilot.
AI-written summary · about
chapters (7)
- 0:00AutoML introduction
- 2:58AWS AutoML services
- 10:04SageMaker Canvas & Autopilot
- 20:21AutoGluon model building
- 27:48AutoGluon features & updates
- 31:20Summary & deployment
- 32:03Q&A
related talks
01h 25mSolving complex ML problems in a few lines of code with AutoGluon
31mUse AutoML to create high-quality models with just a few clicks
31mUse AutoML to create high-quality models with just a few clicks
32mBuild quality ML models easily & quickly with Amazon SageMaker Autopilot
30mBring AutoML to all users across your business
31mTrain and tune ML models to the highest accuracy using Amazon SageMaker
49mUse Amazon SageMaker to build high-quality ML models faster
33mBuild, train, and deploy ML models using Amazon SageMaker