Learn about gradient-based input attribution methods in machine learning through this 37-minute lecture that explores key evaluation metrics and techniques. Begin with a foundational recap of gradient-based highlighting approaches, then dive into plausibility assessment of attribution methods. Examine comprehensive evaluation frameworks including sufficiency metrics, and conclude with advanced concepts like erasure techniques, Remove and Retrain (ROAR), and Recursive-ROAR methodologies for robust model interpretation.
Evaluating Input Attribution Methods in Machine Learning - Plausibility and Comprehensiveness
Overview
Syllabus
Recap: Gradient-based highlights/input attribution so-far
Plausibility
Comprehensiveness & Sufficiency
Erasure, ROAR, Recursive-ROAR
Taught by
UofU Data Science
Related Courses
-
Gradient-Based Input Attribution Methods and Their Applications
-
The Nuts and Bolts of Machine Learning
-
Understand data science for machine learning
-
An Overview of Local Explainability Methods and Their Evaluation in AI
-
Introduction to Machine Learning Model Explanations and Interpretability
-
CMU Neural Nets for NLP: Model Interpretation
