Body
Overview
Visually probe the behavior of trained machine learning models, with minimal coding.
A key challenge in developing and deploying responsible Machine Learning (ML) systems is understanding their performance across a wide range of inputs.
Using the What-If Tool, you can test performance in hypothetical situations, analyze the importance of different data features, and visualize model behavior across multiple models and subsets of input data, and for different ML fairness metrics.
Content Themes
Machine learning, analysis, research
Link to resource
What-If Tool (GitHub.io)