Figure 3 - uploaded by Michele Donini
Content may be subject to copyright.
Download
View publication
Pre-training bias results in Data Wrangler.

Pre-training bias results in Data Wrangler.

Source publication
Figure 2: The stages in a ML lifecycle from problem formulation to...
Figure 3: Pre-training bias results in Data Wrangler.
Figure 4: Post-training bias results in Studio Trials.
Figure 5: SHAP feature importance.
+1 Figure 6: Scaling of SHAP on 100,000 examples and measuring time (left)...
Amazon SageMaker Clarify: Machine Learning Bias Detection and Explainability in the Cloud
Preprint
Full-text available
  • Sep 2021
Understanding the predictions made by machine learning (ML) models and their potential biases remains a challenging and labor-intensive task that depends on the application, the dataset, and the specific model. We present Amazon SageMaker Clarify, an explainability feature for Amazon SageMaker that launched in December 2020, providing insights into...
Cite
Download full-text

Contexts in source publication

Context 1
... we train the model we seek to explore biases in the dataset. Figure 3 shows Clarify integrated into Data Wrangler. Convenient drop-downs are available to select the label column and the group. ...
Context 2
... we train the model we seek to explore biases in the dataset. Figure 3 shows Clarify integrated into Data Wrangler. Convenient drop-downs are available to select the label column and the group. ...