UsefulLinks
Computer Science
Artificial Intelligence
Explainable Artificial Intelligence
1. Foundations of Explainable AI
2. Taxonomy and Classification of XAI Methods
3. Intrinsically Interpretable Models
4. Post-hoc Explanation Methods
5. Deep Learning Specific Explanation Methods
6. Tree Ensemble Specific Methods
7. Evaluation of Explanations
8. Practical Applications of XAI
9. Challenges and Limitations
10. Future Directions and Emerging Trends
6.
Tree Ensemble Specific Methods
6.1.
Feature Importance in Ensembles
6.1.1.
Gini Importance
6.1.1.1.
Impurity Reduction Measurement
6.1.1.2.
Weighted Averaging Across Trees
6.1.2.
Permutation Importance
6.1.2.1.
Out-of-Bag Error Changes
6.1.2.2.
Cross-Validation Approaches
6.1.3.
SHAP TreeExplainer
6.1.3.1.
Efficient Exact Computation
6.1.3.2.
Polynomial Time Algorithm
6.2.
Individual Tree Analysis
6.2.1.
Tree Visualization
6.2.1.1.
Decision Path Representation
6.2.1.2.
Node Importance Analysis
6.2.2.
Tree Diversity Analysis
6.2.2.1.
Prediction Variance Decomposition
6.2.2.2.
Ensemble Agreement Measurement
6.3.
Rule Extraction from Ensembles
6.3.1.
Global Rule Extraction
6.3.1.1.
Ensemble Simplification
6.3.1.2.
Rule Pruning Techniques
6.3.2.
Local Rule Extraction
6.3.2.1.
Instance-Specific Rules
6.3.2.2.
Path Aggregation Methods
Previous
5. Deep Learning Specific Explanation Methods
Go to top
Next
7. Evaluation of Explanations