Explainable AI for Practitioners

Spis treści ebooka

• Foreword
• Preface
  • Who Should Read This Book?
  • What Is and What Is Not in This Book?
  • Code Samples
  • Navigating This Book
  • Conventions Used in This Book
  • OReilly Online Learning
  • How to Contact Us
  • Acknowledgments
• 1. Introduction
  • Why Explainable AI
  • What Is Explainable AI?
  • Who Needs Explainability?
  • Challenges in Explainability
  • Evaluating Explainability
  • How Has Explainability Been Used?
    • How LinkedIn Uses Explainable AI
    • PwC Uses Explainable AI for Auto Insurance Claims
    • Accenture Labs Explains Loan Decisions
    • DARPA Uses Explainable AI to Build Third-Wave AI
  • Summary
• 2. An Overview of Explainability
  • What Are Explanations?
  • Interpretability and Explainability
  • Explainability Consumers
    • PractitionersData Scientists and ML Engineers
    • ObserversBusiness Stakeholders and Regulators
    • End UsersDomain Experts and Affected Users
  • Types of Explanations
    • Premodeling Explainability
    • Intrinsic Versus Post Hoc Explainability
    • Local, Cohort, and Global Explanations
    • Attributions, Counterfactual, and Example-Based Explanations
  • Themes Throughout Explainability
    • Feature Attributions
      • Shapley values
      • Sampled Shapley technique
      • Baselines
      • Gradient-based techniques
      • Saliency maps and feature attributions
    • Surrogate Models
    • Activation
  • Putting It All Together
  • Summary
• 3. Explainability for Tabular Data
  • Permutation Feature Importance
    • Permutation Feature Importance from Scratch
    • Permutation Feature Importance in scikit-learn
  • Shapley Values
    • SHAP (SHapley Additive exPlanations)
    • Visualizing Local Feature Attributions
    • Visualizing Global Feature Attributions
    • Interpreting Feature Attributions from Shapley Values
    • Managed Shapley Values
      • Google Cloud Platform (GCP)Explainable AI
      • Microsoft Azure and AWS SageMaker
  • Explaining Tree-Based Models
    • From Decision Trees to Tree Ensembles
    • SHAPs TreeExplainer
  • Partial Dependence Plots and Related Plots
    • Partial Dependence Plots (PDPs)
      • Working with classification models
      • Assumption of independence
      • Understanding feature distributions
    • Individual Conditional Expectation Plots (ICEs)
    • Accumulated Local Effects (ALE)
  • Summary
• 4. Explainability for Image Data
  • Integrated Gradients (IG)
    • Choosing a Baseline
    • Accumulating Gradients
    • Improvements on Integrated Gradients
      • Blur Integrated Gradients (Blur-IG)
      • Guided Integrated Gradients (Guided IG)
  • XRAI
    • How XRAI Works
    • Implementing XRAI
  • Grad-CAM
    • How Grad-CAM Works
    • Implementing Grad-CAM
    • Improving Grad-CAM
  • LIME
    • How LIME Works
    • Implementing LIME
  • Guided Backpropagation and Guided Grad-CAM
    • Guided Backprop and DeConvNets
    • Guided Grad-CAM
  • Summary
• 5. Explainability for Text Data
  • Overview of Building Models with Text
    • Tokenization
    • Word Embeddings and Pretrained Embeddings
  • LIME
    • How LIME Works with Text
  • Gradient x Input
    • Intuition from Linear Models
    • From Linear to Nonlinear and Text Models
    • Grad L2-norm
      • Comparing sensitivity and saliency methods
  • Layer Integrated Gradients
    • A Variation on Integrated Gradients
  • Layer-Wise Relevance Propagation (LRP)
    • How LRP Works
      • The relationship between LRP and Grad x Input
    • Deriving Explanations from Attention
  • Which Method to Use?
    • Language Interpretability Tool
  • Summary
• 6. Advanced and Emerging Topics
  • Alternative Explainability Techniques
    • Alternate Input Attribution
      • Example-based explanations
      • Influence function-based explanations
      • Concept-based explanations
    • Explainability by Design
      • Explainability via constraints
      • Explainability via distillation
  • Other Modalities
    • Time-Series Data
    • Multimodal Data
  • Evaluation of Explainability Techniques
    • A Theoretical Approach
      • Axiom of completeness
      • Axiom of sensitivity
      • Axiom of implementation invariance
      • Axiom of linearity
      • Axiom of symmetry-preserving
    • Empirical Approaches
      • Basic sanity checks
      • Faithfulness check
      • Synthetic datasets
      • Application specific
  • Summary
• 7. Interacting with Explainable AI
  • Who Uses Explainability?
  • How to Effectively Present Explanations
    • Clarify What, How, and Why the ML Performed the Way It Did
    • Accurately Represent the Explanations
      • Technical accuracy of explanations
      • Brittleness in explanations
    • Build on the ML Consumers Existing Understanding
  • Common Pitfalls in Using Explainability
    • Assuming Causality
    • Overfitting Intent to a Model
    • Overreaching for Additional Explanations
  • Summary
• 8. Putting It All Together
  • Building with Explainability in Mind
    • The ML Life Cycle
      • Explainability through discovery
      • Explainability through development
      • Explainability through deployment
  • AI Regulations and Explainability
  • What to Look Forward To in Explainable AI
    • Natural and Semantic Explanations
    • Interrogative Explanations
    • Targeted Explanations
  • Summary
• A. Taxonomy, Techniques, and Further Reading
  • ML Consumers
  • Taxonomy of Explainability
  • XAI Techniques
    • Tabular Models
    • Image Models
    • Text Models
    • Advanced and Emerging Techniques
  • Interacting with Explainability
  • Putting It All Together
  • Further Reading
    • Explainable AI
    • Interacting with Explainability
    • Technical Accuracy of XAI techniques
    • Brittleness of XAI techniques
    • XAI for DNNs
• Index

pokaż cały spis treści

ukryj recenzje