Search icon CANCEL
Subscription
0
Cart icon
Cart
Close icon
You have no products in your basket yet
Save more on your purchases!
Savings automatically calculated. No voucher code required
Arrow left icon
All Products
Best Sellers
New Releases
Books
Videos
Audiobooks
Learning Hub
Newsletters
Free Learning
Arrow right icon
Arrow up icon
GO TO TOP
Deep Learning and XAI Techniques for Anomaly Detection

You're reading from  Deep Learning and XAI Techniques for Anomaly Detection

Product type Book
Published in Jan 2023
Publisher Packt
ISBN-13 9781804617755
Pages 218 pages
Edition 1st Edition
Languages
Author (1):
Cher Simon Cher Simon
Profile icon Cher Simon
Toc

Table of Contents (15) Chapters close

Preface 1. Part 1 – Introduction to Explainable Deep Learning Anomaly Detection
2. Chapter 1: Understanding Deep Learning Anomaly Detection 3. Chapter 2: Understanding Explainable AI 4. Part 2 – Building an Explainable Deep Learning Anomaly Detector
5. Chapter 3: Natural Language Processing Anomaly Explainability 6. Chapter 4: Time Series Anomaly Explainability 7. Chapter 5: Computer Vision Anomaly Explainability 8. Part 3 – Evaluating an Explainable Deep Learning Anomaly Detector
9. Chapter 6: Differentiating Intrinsic and Post Hoc Explainability 10. Chapter 7: Backpropagation versus Perturbation Explainability 11. Chapter 8: Model-Agnostic versus Model-Specific Explainability 12. Chapter 9: Explainability Evaluation Schemes 13. Index 14. Other Books You May Enjoy

Reviewing the System Causability Scale (SCS)

Created in 1986 by John Brooke, the System Usability Scale (SUS) provides a simple tool to measure the usability of a system’s user interface. It consists of a 10-item questionnaire with 5 response options, allowing respondents to evaluate the quality of products and services from strongly agree to strongly disagree.

Inspired by SUS, SCS, available at https://doi.org/10.1007/s13218-020-00636-z, focuses on measuring the qualitative aspect of XAI systems. SCS meets the XAI principle of meaningfulness by NIST to determine end user perception against explanations provided by XAI systems.

SCS assesses the effectiveness of an XAI user interface in providing explanations to the target audience using a Likert scale questionnaire covering the following scopes:

  • A given explanation offers accurate causal factors with relevant granularity
  • The context of a given explanation makes sense to the user
  • Users can tune the level...
lock icon The rest of the chapter is locked
Register for a free Packt account to unlock a world of extra content!
A free Packt account unlocks extra newsletters, articles, discounted offers, and much more. Start advancing your knowledge today.
Unlock this book and the full library FREE for 7 days
Get unlimited access to 7000+ expert-authored eBooks and videos courses covering every tech area you can think of
Renews at $15.99/month. Cancel anytime