Explainable Artificial Intelligence

  1. Taxonomy and Classification of XAI Methods
    1. Scope of Explanation
      1. Global Explanations
        1. Model-Level Understanding
          1. Feature Importance at Model Level
            1. Model Behavior Summarization
              1. Decision Boundary Analysis
              2. Local Explanations
                1. Instance-Level Predictions
                  1. Feature Attribution for Single Instances
                    1. Local Decision Boundaries
                    2. Cohort Explanations
                      1. Group-Level Analysis
                        1. Subpopulation Behavior
                      2. Timing of Explanation Generation
                        1. Ante-hoc Methods
                          1. Intrinsically Interpretable Models
                            1. Design-Time Interpretability
                              1. Trade-offs with Model Performance
                              2. Post-hoc Methods
                                1. Explanation of Pre-trained Models
                                  1. Retrofitting Interpretability
                                    1. Explanation Generation Algorithms
                                  2. Model Dependency
                                    1. Model-Agnostic Methods
                                      1. Universal Applicability
                                        1. Black-Box Treatment of Models
                                          1. Flexibility and Limitations
                                          2. Model-Specific Methods
                                            1. Architecture-Tailored Approaches
                                              1. Leveraging Internal Model Structures
                                                1. Deep Learning Specific Methods
                                              2. Type of Explanation Output
                                                1. Feature Attribution Methods
                                                  1. Example-Based Explanations
                                                    1. Rule-Based Explanations
                                                      1. Concept-Based Explanations
                                                        1. Counterfactual Explanations
                                                          1. Natural Language Explanations

                                                        Previous

                                                        1. Foundations of Explainable AI

                                                        Go to top

                                                        Next

                                                        3. Intrinsically Interpretable Models