Explainable Deep Learning AI

Methods and Challenges
Erscheinungsjahr 2023
ISBN: 978-0-323-96098-4
Verlag: Elsevier Science & Technology

Buch, Englisch, 395 Seiten, Format (B × H): 234 mm x 189 mm, Gewicht: 698 g

Explainable Deep Learning AI: Methods and Challenges presents the latest works of leading researchers in the XAI area, offering an overview of the XAI area, along with several novel technical methods and applications that address explainability challenges for deep learning AI systems. The book overviews XAI and then covers a number of specific technical works and approaches for deep learning, ranging from general XAI methods to specific XAI applications, and finally, with user-oriented evaluation approaches. It also explores the main categories of explainable AI - deep learning, which become the necessary condition in various applications of artificial intelligence.

The groups of methods such as back-propagation and perturbation-based methods are explained, and the application to various kinds of data classification are presented.

Zielgruppe

<p>This book is intended for researchers, PhD students, and practitioners in the area of Explainable Artificial Intelligence (XAI) specifically related to Deep Learning AI Methods</p>

Autoren/Hrsg.

Petkovic, Dragutin

Bourqui, Romain

Quenot, Georges

Benois-Pineau, Jenny

Fachgebiete

• Mathematik | Informatik EDV | Informatik Informatik Künstliche Intelligenz

Inhaltsverzeichnis

1. Introduction
2. Explainable Deep Learning: Methods, Concepts and New Developments

3. Compact Visualization of DNN Classification Performances for Interpretation and Improvement

4. Explaining How Deep Neural Networks Forget by Deep Visualization

5. Characterizing a scene recognition model by identifying the effect of input features via semantic- wise attribution

6. A Feature Understanding Method for Explanation of Image Classification by Convolutional Neural Networks

7. Explainable Deep Learning for decrypting disease signature in Multiple Sclerosis

8. Explanation of CNN Image Classifiers with Hiding Parts

9. Remove to Improve?

10. Explaining CNN classifier using Association Rule Mining Methods on time-series

11. A Methodology to compare XAI Explanations on Natural Language Processing

12. Improving Malware Detection with Explainable Machine Learning

13. AI Explainability. A Bridge between Machine Vision and Natural Language Processing

14. Explainable Deep Learning for Multimedia Indexing and Retrieval

15. User Tests and Techniques for the Post-Hoc Explainability of Deep Learning Models

16. Conclusion

Über Autor(innen)

Petkovic, Dragutin
Dragutin Petkovic is Professor in the Computer Science department at San Francisco State University, USA.

Quenot, Georges
Senior researcher at CNRS, leader of the MRIM group. Works at the Laboratory of Informatics of Grenoble and Multimedia Information Indexing and Retrieval Group.

Bourqui, Romain
Since 2009 he's been an Associate Professor in the Computer Science Department of the IUT ("Technical School"), University of Bordeaux (Talence), France. He is also deputy director of the BKB ("Bench to Knowledge and Beyond") team of LaBRI.