AWS Summit Berlin
The Community Stage at the AWS Summit in Berlin, and the first time I spoke outside Austria.
On the programme
Small Data Machine Learning
2022 · Berlin
With Alexander Zehetmaier. Effective ML systems can be built on limited datasets given the right processes, data handling and coding practices: feature engineering, data augmentation and pre-trained models.
- Slides coming soon
- Read the recap
- Have me give this talk
The services doing the work
Read off the slides, not guessed. Each card says what that service did in this build, and links to the page explaining the capability and how to run it somewhere else.
Amazon SageMaker Feature Store
Feature engineering kept in one place, because how you represent the problem matters more than the model when data is scarce.
Amazon SageMaker
Training and the active-learning loop: collect, train, validate, error analysis, repeat on one to two week cycles.
Where all of this comes from
Every claim on this page traces back to the deck, the recap or the event’s own site.
Everything here is free to read, use and share. No email needed for the slides. If you reuse something, please credit the source.
This page mirrors the talk page on lindamohamed.com, where it was first published.