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

✍ Scribed by Cher Simon

• Publisher: Packt Publishing
• Tongue: English
• Leaves: 218
• Category: Library

✦ Synopsis

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.

Table of Contents

1. Understanding Deep Learning Anomaly Detection
2. Understanding Explainable AI
3. Natural Language Processing Anomaly Explainability
4. Time Series Anomaly Explainability
5. Computer Vision Anomaly Explainability
6. Differentiating Intrinsic versus Post Hoc Explainability
7. Backpropagation Versus Perturbation Explainability
8. Model-Agnostic versus Model-Specific Explainability
9. Explainability Evaluation Schemes

✦ Table of Contents

Cover
Title Page
Copyright and Credits
Foreword
Contributors
Table of Contents
Preface
Part 1 – Introduction to Explainable Deep Learning Anomaly Detection
Chapter 1: Understanding Deep Learning Anomaly Detection
Technical Requirements
Exploring types of anomalies
Discovering real-world use cases
Detecting fraud
Predicting industrial maintenance
Diagnosing medical conditions
Monitoring cybersecurity threats
Reducing environmental impact
Recommending financial strategies
Considering when to use deep learning and what for
Understanding challenges and opportunities
Summary
Chapter 2: Understanding Explainable AI
Understanding the basics of XAI
Differentiating explainability versus interpretability
Contextualizing stakeholder needs
Implementing XAI
Reviewing XAI significance
Considering the right to explanation
Driving inclusion with XAI
Mitigating business risks
Choosing XAI techniques
Summary
Part 2 – Building an Explainable Deep Learning Anomaly Detector
Chapter 3: Natural Language Processing Anomaly Explainability
Technical requirements
Understanding natural language processing
Reviewing AutoGluon
Problem
Solution walk-through
Exercise
Chapter 4: Time Series Anomaly Explainability
Understanding time series
Understanding explainable deep anomaly detection for time series
Technical requirements
The problem
Solution walkthrough
Exercise
Summary
Chapter 5: Computer Vision Anomaly Explainability
Reviewing visual anomaly detection
Reviewing image-level visual anomaly detection
Reviewing pixel-level visual anomaly detection
Integrating deep visual anomaly detection with XAI
Technical requirements
Problem
Solution walkthrough
Exercise
Summary
Part 3 – Evaluating an Explainable Deep Learning Anomaly Detector
Chapter 6: Differentiating Intrinsic and Post hoc Explainability
Technical requirements
Understanding intrinsic explainability
Intrinsic global explainability
Intrinsic local explainability
Understanding post hoc explainability
Post hoc global explainability
Post hoc local explainability
Considering intrinsic versus post hoc explainability
Summary
Chapter 7: Backpropagation versus Perturbation Explainability
Reviewing backpropagation explainability
Saliency maps
Reviewing perturbation explainability
LIME
Comparing backpropagation and perturbation XAI
Summary
Chapter 8: Model-Agnostic versus Model-Specific Explainability
Chapter 9: Explainability Evaluation Schemes
Reviewing the System Causability Scale (SCS)
Exploring Benchmarking Attribution Methods (BAM)
Understanding faithfulness and monotonicity
Human-grounded evaluation framework
Summary
Index
Other Books You May Enjoy