Explainable Deep Learning AI
Methods and Challenges
- 1st Edition - February 20, 2023
- Imprint: Academic Press
- Editors: Jenny Benois-Pineau, Romain Bourqui, Dragutin Petkovic, Georges Quenot
- Language: English
- Paperback ISBN:9 7 8 - 0 - 3 2 3 - 9 6 0 9 8 - 4
- eBook ISBN:9 7 8 - 0 - 3 2 3 - 9 9 3 8 8 - 3
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 n… Read more
Purchase options
Institutional subscription on ScienceDirect
Request a sales quoteExplainable 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.
- Provides an overview of main approaches to Explainable Artificial Intelligence (XAI) in the Deep Learning realm, including the most popular techniques and their use, concluding with challenges and exciting future directions of XAI
- Explores the latest developments in general XAI methods for Deep Learning
- Explains how XAI for Deep Learning is applied to various domains like images, medicine and natural language processing
- Provides an overview of how XAI systems are tested and evaluated, specially with real users, a critical need in XAI
Researchers, PhD students, and practitioners in the area of Explainable Artificial Intelligence (XAI) specifically related to Deep Learning AI Methods
- Cover image
- Title page
- Table of Contents
- Copyright
- List of contributors
- Preface
- Chapter 1: Introduction
- Abstract
- Chapter 2: Explainable deep learning: concepts, methods, and new developments
- Abstract
- Acknowledgement
- 2.1. Introduction
- 2.2. Concepts
- 2.3. Methods
- 2.4. New developments
- 2.5. Limitations and future work
- References
- Chapter 3: Compact visualization of DNN classification performances for interpretation and improvement
- Abstract
- Acknowledgements
- 3.1. Introduction
- 3.2. Previous works
- 3.3. Proposed method for compact visualization of DNN classification performances
- 3.4. Experimental protocol
- 3.5. Results and discussion
- 3.6. Conclusion
- References
- Chapter 4: Characterizing a scene recognition model by identifying the effect of input features via semantic-wise attribution
- Abstract
- Acknowledgements
- 4.1. Introduction
- 4.2. Semantic-wise attribution
- 4.3. Experimental results
- 4.4. Conclusions
- References
- Chapter 5: A feature understanding method for explanation of image classification by convolutional neural networks
- Abstract
- Acknowledgements
- 5.1. Introduction
- 5.2. Principles of white-box explanation methods
- 5.3. Explanation methods
- 5.4. The proposed improvement – modified FEM
- 5.5. Experimental results
- 5.6. Conclusion
- References
- Chapter 6: Explainable deep learning for decrypting disease signatures in multiple sclerosis
- Abstract
- Acknowledgements
- 6.1. Introduction
- 6.2. State-of-the-art
- 6.3. Materials and methods
- 6.4. Results
- 6.5. Discussion
- 6.6. Conclusions
- References
- Chapter 7: Explanation of CNN image classifiers with hiding parts
- Abstract
- Acknowledgements
- 7.1. Introduction
- 7.2. Explanation methods
- 7.3. Recursive division approach
- 7.4. Quality of the model
- 7.5. Experimental modeling
- 7.6. Conclusion
- References
- Chapter 8: Remove to improve?
- Abstract
- Glossary
- Acknowledgements
- 8.1. Introduction
- 8.2. Previous work
- 8.3. Definitions
- 8.4. Experiments
- 8.5. Model selection
- 8.6. Discussion and conclusions
- References
- Chapter 9: Explaining CNN classifier using association rule mining methods on time-series
- Abstract
- 9.1. Introduction
- 9.2. Related work
- 9.3. Background
- 9.4. Methods
- 9.5. Evaluation metrics
- 9.6. Experimental results
- 9.7. Conclusion and future work
- References
- Chapter 10: A methodology to compare XAI explanations on natural language processing
- Abstract
- Glossary
- 10.1. Introduction
- 10.2. Related works
- 10.3. Generating explanations
- 10.4. Evaluation without end users
- 10.5. Psychometric user study
- 10.6. Conclusion
- References
- Chapter 11: Improving malware detection with explainable machine learning
- Abstract
- 11.1. Introduction
- 11.2. Background
- 11.3. Explanation methods
- 11.4. Explaining Android ransomware
- 11.5. Experimental analysis
- 11.6. Discussion
- 11.7. Conclusion
- References
- Chapter 12: Explainability in medical image captioning
- Abstract
- Acknowledgement
- 12.1. Introduction
- 12.2. Related work
- 12.3. Methodology
- 12.4. Experimental results
- 12.5. Conclusion and future work
- References
- Chapter 13: User tests & techniques for the post-hoc explanation of deep learning
- Abstract
- Acknowledgements
- 13.1. Introduction
- 13.2. Post-hoc explanations using factual examples
- 13.3. Counterfactual & semifactual explanations: images
- 13.4. Contrastive explanations: time series
- 13.5. User studies on contrastive explanations
- 13.6. Conclusions
- References
- Chapter 14: Theoretical analysis of LIME
- Abstract
- Acknowledgements
- 14.1. Introduction
- 14.2. LIME for images
- 14.3. LIME for text data
- 14.4. LIME for tabular data
- 14.5. Conclusion
- References
- Chapter 15: Conclusion
- Abstract
- Index
- Edition: 1
- Published: February 20, 2023
- No. of pages (Paperback): 346
- No. of pages (eBook): 346
- Imprint: Academic Press
- Language: English
- Paperback ISBN: 9780323960984
- eBook ISBN: 9780323993883
JB
Jenny Benois-Pineau
Jenny Benois-Pineau is a professor of computer science at the University of Bordeaux and head of the “Video Analysis and Indexing” research group of the “Image and Sound” team of LABRI UMR 58000 Université Bordeaux / CNRS / IPB-ENSEIRB. She was deputy scientific director of theme B of the French national research unit CNRS GDR ISIS (2008-2015) and is currently in charge of international relations at the College of Sciences and Technologies of the University of Bordeaux. She obtained her doctorate in Signals and Systems in Moscow and her Habilitation to Direct Research in Computer Science and Image Processing at the University of Nantes in France. Her subjects of interest include image and video analysis and indexing, artificial intelligence methods applied to image recognition.
Affiliations and expertise
Professor, Labri/University Bordeaux, FranceRB
Romain Bourqui
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.
Affiliations and expertise
Associate Professor, Labri/University Bordeaux, FranceDP
Dragutin Petkovic
Dragutin Petkovic is Professor in the Computer Science department at San Francisco State University, USA.
Affiliations and expertise
Professor, Computer Science department, San Francisco State University, USAGQ
Georges Quenot
Senior researcher at CNRS, leader of the MRIM group. Works at the Laboratory of Informatics of Grenoble and Multimedia Information Indexing and Retrieval Group.
Affiliations and expertise
Senior Researcher, Laboratory of Informatics of Grenoble and Multimedia Information Indexing and Retrieval Group, leader of the MRIM group, CNRS, FranceRead Explainable Deep Learning AI on ScienceDirect