Partial Dependence Plots

Partial Dependence Mutates the Dataset

Training a Global Surrogate

Limitations of Explanation Methods

Stakeholders and Audiences for Explanations

Interpretability Tools and Libraries

Evaluating the Quality of Explanations

Attention as an Explanation and Its Caveats

Surrogate Models for Explaining Black Boxes

Counterfactual Explanations

Saliency Maps for Deep Models

Individual Conditional Expectation Plots

Partial Dependence Plots (PDP)

LIME: Local Model Explanations

SHAP Values and Shapley Explanations

Permutation Feature Importance

Feature Importance Methods

The Accuracy-Interpretability Tradeoff

White-Box Models: Linear & Trees

Model-Agnostic vs Model-Specific Methods

Global vs Local Explanations

Intrinsic vs Post-Hoc Interpretability

Why Model Interpretability Matters

Anchor Rule Precision

Normalizing Attention Weights

Choosing an Attribution Baseline

Faithfulness by Feature Removal

Correlation as Attribution

Counterfactual Search Loop

Example-Based Explanations

LIME Explanations

Feature Importance Concept

Surrogate Models

Interpreting Decision Trees

Right to Explanation

Faithfulness of Explanations

ICE Plots

Attention as Explanation

Interpretability vs Explainability

Counterfactual Explanations

Saliency Maps

Global vs Local Explanations

Linear Model Coefficients

SHAP and Shapley Values

What Interpretability Means

Model-Agnostic vs Model-Specific

Interpretable vs Black-Box Models

Permutation Feature Importance

Accuracy-Interpretability Trade-off

Stakeholder-Appropriate Explanations

Partial Dependence Plots

ICE Curves Collapsed Into a PDP

Integrated Gradients Missing Input Difference

Grad-CAM Averages Over Wrong Axis

LIME Surrogate Ignores Proximity Weights

Perturbation Explanation Predicts Wrong Input

Ranking SHAP Contributions by Impact

Saliency Map Keeps Signed Gradients

Most Important Linear Coefficient

Permutation Feature Importance Sign

SHAP Additivity Check

Global Importance Over Whole Dataset

Averaging Shapley Marginal Contributions

Reconstructing a Prediction from SHAP

Classifying Intrinsic vs Post-Hoc Methods

Odds Ratio from Logistic Coefficient

Linear Model Coefficients

Evaluating Explanation Quality

Chain-of-Thought as Explanation

Grad-CAM for CNNs

Faithfulness vs Plausibility

Attention as Explanation

Pitfalls of Explanation Methods

Counterfactual Explanations

ICE Plots

Saliency Maps

Surrogate Models

LIME

Interpretability vs Explainability

White-Box Models

Permutation Feature Importance

Model-Specific vs Model-Agnostic

Global vs Local Explanations

Why Interpretability Matters

Accuracy-Interpretability Tradeoff

SHAP

Intrinsic vs Post-hoc

Feature Importance