Amazon SageMaker offers features to improve your machine learning (ML) models by detecting potential bias and helping to explain the predictions that your models make from your tabular, computer vision, natural processing, or time series datasets as well as providing purpose-built ML governance tools for managing control access, activity tracking, and reporting across the ML lifecycle.
- Explaining Autopilot Models
- Explaining Image Classification with SageMaker Clarify
- NLP Online Explainability with SageMaker Clarify
- Explaining Object Detection model with Amazon SageMaker Clarify
- SageMaker Clarify Online Explainability on Multi-Model Endpoint
- Tabular Online Explainability with SageMaker Clarify
- Explaining text sentiment analysis using SageMaker Clarify
- TimeSeries Bring Your Own Model
- Amazon SageMaker Model Governance - Model Cards
- Amazon SageMaker Model Governance - Model Cards Model Registry integration
- Fairness and Explainability with SageMaker Clarify - Bring Your Own Container
- Fairness and Explainability with SageMaker Clarify using AWS SDK for Python (Boto3)