Explore SHAP (SHapley Additive exPlanations) and Shapley Values in this 21-minute video tutorial on interpretable machine learning and explainable AI (XAI). Learn why SHAP is necessary, understand its core concepts, and see how it works for local interpretation through practical examples. Dive into Python code for calculating Shapley Values and creating visualizations. Discover alternatives to SHAP and gain insights into making machine learning models more transparent and explainable. Perfect for data scientists and machine learning enthusiasts looking to enhance their understanding of model interpretability techniques.
SHAP and Shapley Values for Interpretable Machine Learning - Kaggle 30 Days of ML Day 18
1littlecoder via YouTube
Overview
Syllabus
Kaggle 30 Days of ML (Day 18) - SHAP - Shapley Values - Interpretable Machine Learning - XAI
Taught by
1littlecoder
Related Courses
-
Explainable deep learning models for healthcare - CDSS 3
-
Understanding SHAP Summary Plot - Interpretable Machine Learning - Day 19
-
Interpretable Machine Learning Applications: Part 2
-
What is Interpretable Machine Learning - ML Explainability - with Python LIME Shap Tutorial
-
Interpretable Machine Learning Applications: Part 1
-
Partial Dependence Plots in Machine Learning Explainability - Day 17 of Kaggle's 30 Days of ML
