Objective criteria for explanations of machine learning models
Abstract Objective criteria to evaluate the performance of machine learning (ML) model explanations are a critical ingredient in bringing greater rigor to the field of explainable artificial intelligence. In this article, we survey three of our proposed criteria that each target different classes of...
Main Authors: | Chih‐Kuan Yeh, Pradeep Ravikumar |
---|---|
Format: | Article |
Language: | English |
Published: |
Wiley
2021-12-01
|
Series: | Applied AI Letters |
Subjects: | |
Online Access: | https://doi.org/10.1002/ail2.57 |
Similar Items
-
TextFocus: Assessing the Faithfulness of Feature Attribution Methods Explanations in Natural Language Processing
by: Ettore Mariotti, et al.
Published: (2024-01-01) -
Local Explanations of Global Rankings: Insights for Competitive Rankings
by: Hadis Anahideh, et al.
Published: (2022-01-01) -
PCAIME: Principal Component Analysis-Enhanced Approximate Inverse Model Explanations Through Dimensional Decomposition and Expansion
by: Takafumi Nakanishi
Published: (2024-01-01) -
Explainability of Machine Learning Models for Bankruptcy Prediction
by: Min Sue Park, et al.
Published: (2021-01-01) -
Rapid Visual Screening Feature Importance for Seismic Vulnerability Ranking via Machine Learning and SHAP Values
by: Ioannis Karampinis, et al.
Published: (2024-03-01)