Learn how to debias AI with Amazon SageMaker. Build machine learning models that are fair, transparent, and explainable.
Overview
Syllabus
Introduction
- Debiasing AI using Amazon SageMaker
- What you should know
- Predictive policing
- Overview of crime-fighting case study
- Architecture diagram
- Tools, services, and costs
- Terms and concepts
- Demo of Amazon SageMaker
- What is SageMaker?
- Machine learning process
- Inspect and visualize data
- Prepare the data
- Train the model
- Deploy the model
- What is DeepLens?
- Deploy model to AWS DeepLens
- Extend AWS DeepLens
- Retrieve attributes via AWS Rekognition
- Invoke the crime model
- Set up model alerts
- What is explainable AI (XAI)?
- Trust and transparency issues
- Making algorithms explainable
- Next steps
Taught by
Kesha Williams