Deep Learning and XAI Techniques for Anomaly Detection: Integrate the theory and practice of deep anomaly explainability

Cover Page....2

Table of Contents....3

Preface....4

Part 1 – Introduction to Explainable Deep Learning Anomaly Detection....12

Chapter 1: Understanding Deep Learning Anomaly Detection....13

Technical requirements....14

Exploring types of anomalies....15

Discovering real-world use cases....26

Considering when to use deep learning and what for....41

Understanding challenges and opportunities....44

Summary....46

Chapter 2: Understanding Explainable AI....47

Understanding the basics of XAI....48

Reviewing XAI significance....60

Choosing XAI techniques....65

Summary....66

Part 2 – Building an Explainable Deep Learning Anomaly Detector....68

Chapter 3: Natural Language Processing Anomaly Explainability....69

Technical requirements....71

Understanding natural language processing....72

Problem....88

Solution walk-through....88

Exercise....110

Chapter 4: Time Series Anomaly Explainability....117

Understanding time series....118

Understanding explainable deep anomaly detection for time series....120

Technical requirements....122

The problem....123

Solution walkthrough....123

Exercise....146

Summary....146

Chapter 5: Computer Vision Anomaly Explainability....147

Reviewing visual anomaly detection....148

Integrating deep visual anomaly detection with XAI....151

Technical requirements....153

Problem....154

Solution walkthrough....155

Exercise....177

Summary....178

Part 3 – Evaluating an Explainable Deep Learning Anomaly Detector....179

Chapter 6: Differentiating Intrinsic and Post Hoc Explainability....180

Technical requirements....181

Understanding intrinsic explainability....182

Understanding post hoc explainability....184

Considering intrinsic versus post hoc explainability....195

Summary....196

Chapter 7: Backpropagation versus Perturbation Explainability....197

Reviewing backpropagation explainability....198

Reviewing perturbation explainability....207

Comparing backpropagation and perturbation XAI....221

Summary....223

Chapter 8: Model-Agnostic versus Model-Specific Explainability....224

Technical requirements....224

Reviewing model-agnostic explainability....226

Reviewing model-specific explainability....250

Choosing an XAI method....260

Summary....262

Chapter 9: Explainability Evaluation Schemes....264

Reviewing the System Causability Scale (SCS)....266

Exploring Benchmarking Attribution Methods (BAM)....267

Understanding faithfulness and monotonicity....270

Human-grounded evaluation framework....275

Summary....276

Index....278

Why subscribe?....294

Other Books You May Enjoy....295

Packt is searching for authors like you....299

Share Your Thoughts....299

Download a free PDF copy of this book....300

Create interpretable AI models for transparent and explainable anomaly detection with this hands-on guide

Purchase of the print or Kindle book includes a free PDF eBook

Key Features

• Build auditable XAI models for replicability and regulatory compliance
• Derive critical insights from transparent anomaly detection models
• Strike the right balance between model accuracy and interpretability

Book Description

Despite promising advances, the opaque nature of deep learning models makes it difficult to interpret them, which is a drawback in terms of their practical deployment and regulatory compliance.

Deep Learning and XAI Techniques for Anomaly Detection shows you state-of-the-art methods that'll help you to understand and address these challenges. By leveraging the Explainable AI (XAI) and deep learning techniques described in this book, you'll discover how to successfully extract business-critical insights while ensuring fair and ethical analysis.

This practical guide will provide you with tools and best practices to achieve transparency and interpretability with deep learning models, ultimately establishing trust in your anomaly detection applications. Throughout the chapters, you'll get equipped with XAI and anomaly detection knowledge that'll enable you to embark on a series of real-world projects. Whether you are building computer vision, natural language processing, or time series models, you'll learn how to quantify and assess their explainability.

By the end of this deep learning book, you'll be able to build a variety of deep learning XAI models and perform validation to assess their explainability.

What You Will Learn:

• Explore deep learning frameworks for anomaly detection
• Mitigate bias to ensure unbiased and ethical analysis
• Increase your privacy and regulatory compliance awareness
• Build deep learning anomaly detectors in several domains
• Compare intrinsic and post hoc explainability methods
• Examine backpropagation and perturbation methods
• Conduct model-agnostic and model-specific explainability techniques
• Evaluate the explainability of your deep learning models

Who this book is for:

This book is for anyone who aspires to explore explainable deep learning anomaly detection, tenured data scientists or ML practitioners looking for Explainable AI (XAI) best practices, or business leaders looking to make decisions on trade-off between performance and interpretability of anomaly detection applications. A basic understanding of deep learning and anomaly detection-related topics using Python is recommended to get the most out of this book.