Deep learning and XAI techniques for anomaly detection : integrating the theory and practice of deep anomaly explainability / Cher Simon and Jeff Barr.

Format:

Book

Author/Creator:

Simon, Cher, author.

Barr, Jeff, author.

Language:

English

Subjects (All):

Machine learning--Industrial applications.

Machine learning.

Anomaly detection (Computer security).

Physical Description:

1 online resource (218 pages)

Edition:

1st ed.

Place of Publication:

Birmingham, England : Packt Publishing, Limited, [2023]

Biography/History:

Simon Cher: Cher Simon is a principal solutions architect specializing in artificial intelligence, machine learning, and data analytics at AWS. Cher has 20 years of experience in architecting enterprise-scale, data-driven, and AI-powered industry solutions. Besides building cloud-native solutions in her day-to-day role with customers, Cher is also an avid writer and a frequent speaker at AWS conferences. Barr Jeff: Contacted on 3/2/2017 for AWS for Architects by Nishit Shetty

Summary:

Deep Learning and XAI Techniques for Anomaly Detection shows you how to evaluate and create explainable models, leading to increased interpretability and trust in model predictions with better performance. You'll explore the fundamentals of deep learning, anomaly detection, and XAI using practical examples and self-assessment questions.

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

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

The problem

Solution walkthrough

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

Summary.

Part 3 - Evaluating an Explainable Deep Learning Anomaly Detector

Chapter 6: Differentiating Intrinsic and Post hoc Explainability

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

Chapter 7: Backpropagation versus Perturbation Explainability

Reviewing backpropagation explainability

Saliency maps

Reviewing perturbation explainability

LIME

Comparing backpropagation and perturbation XAI

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

Index

Other Books You May Enjoy.

Notes:

Includes index.

Description based on print version record.

ISBN:

9781804613375

1804613371

OCLC:

1369031260