Explainable Artificial Intelligence

Chapter 1 XAI Requirements in Smart Production Processes: A Case Study

Chapter 2 Perlocution vs Illocution: How Different Interpretations of the Act of Explaining Impact on the Evaluation of Explanations and XAI

Chapter 3 Dear XAI Community, We Need to Talk!

Chapter 4 Speeding Things Up. Can Explainability Improve Human Learning?

Chapter 5 Statutory Professions in AI Governance and Their Consequences for Explainable AI

Chapter 6 The Xi Method: Unlocking the Mysteries of Regression with Statistics

Chapter 7 Do Intermediate Feature Coalitions Aid Explainability of Black-Box Models?

Chapter 8 Unfooling SHAP and SAGE: Knockoff Imputation for Shapley Values

Chapter 9 Strategies to Exploit XAI to Improve Classification Systems

Chapter 10 Beyond Prediction Similarity: ShapGAP for Evaluating Faithful Surrogate Models in XAI

Chapter 11 iPDP: On Partial Dependence Plots in Dynamic Modeling Scenarios

Chapter 12 SAC-FACT: Soft Actor-Critic Reinforcement Learning for Counterfactual Explanations

Chapter 13 Algorithm-Agnostic Feature Attributions for Clustering

Chapter 14 Feature Importance versus Feature Influence and What It Signifies for Explainable AI

Chapter 15 ABC-GAN: Spatially Constrained Counterfactual Generation for Image Classification Explanations

Chapter 16 The Importance of Time in Causal Algorithmic Recourse

Chapter 17 Explaining Model Behavior with Global Causal Analysis

Chapter 18 Counterfactual Explanations for Graph Classification Through the Lenses of Density

Chapter 19 Ablation Path Saliency

Chapter 20 IxDRL: A Novel Explainable Deep Reinforcement Learning Toolkit Based on Analyses of Interestingness

Chapter 21 The Co-12 Recipe for Evaluating Interpretable Part-Prototype Image Classifiers

Chapter 22 Reason to Explain: Interactive Contrastive Explanations ( REASONX )

Chapter 23 Sanity Checks for Saliency Methods Explaining Object Detectors

Chapter 24 Relating the Partial Dependence Plot and Permutation Feature Importance to the Data Generating Process

Chapter 25 Evaluating Feature Relevance XAI in Network Intrusion Detection

Chapter 26 Cost of Explainability in AI: An Example with Credit Scoring Models

Chapter 27 Lorenz Zonoids for Trustworthy AI

Chapter 28 Explainable Machine Learning for Bag of Words-Based Phishing Detection

Chapter 29 An Evaluation of Contextual Importance and Utility for Outcome Explanation of Black-Box Predictions for Medical Datasets

Chapter 30 Evaluating Explanations of an Alzheimer’s Disease 18F-FDG Brain PET Black-Box Classifier

Chapter 31 The Accuracy and Faithfullness of AL-DLIME - Active Learning-Based Deterministic Local Interpretable Model-Agnostic Explanations: A Comparison with LIME and DLIME in Medicine

Chapter 32 Understanding Unsupervised Learning Explanations Using Contextual Importance and Utility

Chapter 33 Color Shadows 2: Assessing the Impact of XAI on Diagnostic Decision-Making

Chapter 34 Federated Learning of Explainable Artificial Intelligence Models for Predicting Parkinson’s Disease Progression

Chapter 35 An Interactive XAI Interface with Application in Healthcare for Non-experts

Chapter 36 Selecting Textural Characteristics of Chest X-Rays for Pneumonia Lesions Classification with the Integrated Gradients XAI Attribution Method