book

Explainable AI for Practitioners

by Michael Munn, David Pitman

October 2022

Beginner to intermediate

276 pages

8h 32m

English

O'Reilly Media, Inc.

Book available

Read now

Unlock full access

Who Should Read This Book?What Is and What Is Not in This Book?Code SamplesNavigating This BookConventions Used in This BookO’Reilly Online LearningHow to Contact UsAcknowledgments
Why Explainable AIWhat Is Explainable AI?Who Needs Explainability?Challenges in ExplainabilityEvaluating ExplainabilityHow Has Explainability Been Used?How LinkedIn Uses Explainable AIPwC Uses Explainable AI for Auto Insurance ClaimsAccenture Labs Explains Loan DecisionsDARPA Uses Explainable AI to Build “Third-Wave AI”Summary
What Are Explanations?Interpretability and ExplainabilityExplainability ConsumersPractitioners—Data Scientists and ML EngineersObservers—Business Stakeholders and RegulatorsEnd Users—Domain Experts and Affected UsersTypes of ExplanationsPremodeling ExplainabilityIntrinsic Versus Post Hoc ExplainabilityLocal, Cohort, and Global ExplanationsAttributions, Counterfactual, and Example-Based ExplanationsThemes Throughout ExplainabilityFeature AttributionsSurrogate ModelsActivationPutting It All TogetherSummary
Permutation Feature ImportancePermutation Feature Importance from ScratchPermutation Feature Importance in scikit-learnShapley ValuesSHAP (SHapley Additive exPlanations)Visualizing Local Feature AttributionsVisualizing Global Feature AttributionsInterpreting Feature Attributions from Shapley ValuesManaged Shapley ValuesExplaining Tree-Based ModelsFrom Decision Trees to Tree EnsemblesSHAP’s TreeExplainerPartial Dependence Plots and Related PlotsPartial Dependence Plots (PDPs)Individual Conditional Expectation Plots (ICEs)Accumulated Local Effects (ALE)Summary
Integrated Gradients (IG)Choosing a BaselineAccumulating GradientsImprovements on Integrated GradientsXRAIHow XRAI WorksImplementing XRAIGrad-CAMHow Grad-CAM WorksImplementing Grad-CAMImproving Grad-CAMLIMEHow LIME WorksImplementing LIMEGuided Backpropagation and Guided Grad-CAMGuided Backprop and DeConvNetsGuided Grad-CAMSummary
Overview of Building Models with TextTokenizationWord Embeddings and Pretrained EmbeddingsLIMEHow LIME Works with TextGradient x InputIntuition from Linear ModelsFrom Linear to Nonlinear and Text ModelsGrad L2-normLayer Integrated GradientsA Variation on Integrated GradientsLayer-Wise Relevance Propagation (LRP)How LRP WorksDeriving Explanations from AttentionWhich Method to Use?Language Interpretability ToolSummary
Alternative Explainability TechniquesAlternate Input AttributionExplainability by DesignOther ModalitiesTime-Series DataMultimodal DataEvaluation of Explainability TechniquesA Theoretical ApproachEmpirical ApproachesSummary
Who Uses Explainability?How to Effectively Present ExplanationsClarify What, How, and Why the ML Performed the Way It DidAccurately Represent the ExplanationsBuild on the ML Consumer’s Existing UnderstandingCommon Pitfalls in Using ExplainabilityAssuming CausalityOverfitting Intent to a ModelOverreaching for Additional ExplanationsSummary
Building with Explainability in MindThe ML Life CycleAI Regulations and ExplainabilityWhat to Look Forward To in Explainable AINatural and Semantic ExplanationsInterrogative ExplanationsTargeted ExplanationsSummary

ML ConsumersTaxonomy of ExplainabilityXAI TechniquesTabular ModelsImage ModelsText ModelsAdvanced and Emerging TechniquesInteracting with ExplainabilityPutting It All TogetherFurther ReadingExplainable AIInteracting with ExplainabilityTechnical Accuracy of XAI techniquesBrittleness of XAI techniquesXAI for DNNs

Content preview from Explainable AI for Practitioners

Appendix. Taxonomy, Techniques, and Further Reading

To aid you in using this book in the future, we have put together a brief review of the topics and techniques covered in this book. You can use these guides and tables as a reference in the future to help you quickly survey your options for a new problem before diving into more detail.

ML Consumers

There are three types of users who consume and interact with ML:

ML practitioners: Data scientists and ML engineers that build, develop, tune, deploy, and operationalize a model.
Observers: Business stakeholders and regulators who are not involved in the engineering of the model, but also are not using the model in deployment. They use explanations to validate model performance and build trust that a model is working as expected.
End users: Domain experts and affected users who use, or are impacted by, a model’s predictions. They may have a deep understanding of the context the model operates in or may be affected by the result of a model’s prediction, with little background knowledge in ML or the domain.

Taxonomy of Explainability

There are several characteristics that help define the field of explainability. These are:

Explainability versus interpretability: Although sometimes used interchangeably in industry, we define explainability as techniques that explain a model based on a prediction (or group of predictions). The technique does not need to understand how the model itself works, although it may rely on aspects of a model’s ...