Explore fairness in machine learning models through a comprehensive tutorial presented at FAT*2020 in Barcelona. Dive into the What-if Tool and SHAP (SHapley Additive exPlanations) to gain practical insights on assessing and improving model fairness. Learn from Google experts James Wexler and Andrew Zaldivar as they demonstrate interactive techniques for probing ML models. Watch an in-depth demo showcasing real-world applications, and access accompanying slides for further study. Enhance your understanding of ethical AI practices and develop skills to create more equitable machine learning systems.
Probing ML Models for Fairness with the What-if Tool and SHAP
Association for Computing Machinery (ACM) via YouTube
Overview
Syllabus
Probing ML models for fairness with the What-if Tool and SHAP
Taught by
ACM FAccT Conference
Related Courses
-
Mitigating Bias in Models with SHAP and Fairlearn
-
Responsible & Safe AI Systems
-
Understanding SHAP Summary Plot - Interpretable Machine Learning - Day 19
-
SHAP and Shapley Values for Interpretable Machine Learning - Kaggle 30 Days of ML Day 18
-
What is Interpretable Machine Learning - ML Explainability - with Python LIME Shap Tutorial
-
Evaluating Fairness of Machine Learning Models Under Uncertain and Incomplete Information
