Skip to main content
Book cover
  • Book
  • Open Access
  • © 2022

xxAI - Beyond Explainable AI

International Workshop, Held in Conjunction with ICML 2020, July 18, 2020, Vienna, Austria, Revised and Extended Papers

Editors:

  1. Andreas Holzinger

    1. University of Natural Resources and Life Sciences Vienna, Vienna, Austria

    View editor publications

    You can also search for this editor in PubMed   Google Scholar

  2. Randy Goebel

    1. University of Alberta, Edmonton, Canada

    View editor publications

    You can also search for this editor in PubMed   Google Scholar

  3. Ruth Fong

    1. Princeton University, Princeton, USA

    View editor publications

    You can also search for this editor in PubMed   Google Scholar

  4. Taesup Moon

    1. Seoul National University, Seoul, Korea (Republic of)

    View editor publications

    You can also search for this editor in PubMed   Google Scholar

  5. Klaus-Robert Müller

    1. Technische Universität Berlin, Berlin, Germany

    View editor publications

    You can also search for this editor in PubMed   Google Scholar

  6. Wojciech Samek

    1. Fraunhofer Heinrich Hertz Institute, Berlin, Germany

    View editor publications

    You can also search for this editor in PubMed   Google Scholar

  • This book is open access, which means that you have free and unlimited access.

  • Explainable AI (xAI) aims to create tools and models that are predictive, interpretable, understandable for humans

  • Topic receiving huge interest in the machine learning and AI research communities

  • Contributions in this volume are from leading researchers in the field, drawn from both academia and industry

Part of the book series: Lecture Notes in Computer Science (LNCS, volume 13200)

Part of the book sub series: Lecture Notes in Artificial Intelligence (LNAI)

Conference series link(s): xxAI: International Workshop on Extending Explainable AI Beyond Deep Models and Classifiers

Conference proceedings info: xxAI 2020.

Sections

Softcover Book USD 49.99
Price excludes VAT (USA)
Learn about institutional subscriptions

Table of contents (18 chapters)

  1. Front Matter

    Pages i-x
    PDF

  2. Editorial

    1. Front Matter

      Pages 1-1
      PDF

    2. xxAI - Beyond Explainable Artificial Intelligence

      • Andreas Holzinger, Randy Goebel, Ruth Fong, Taesup Moon, Klaus-Robert Müller, Wojciech Samek
      Pages 3-10Open Access

  3. Current Methods and Challenges

    1. Front Matter

      Pages 11-11
      PDF

    2. Explainable AI Methods - A Brief Overview

      • Andreas Holzinger, Anna Saranti, Christoph Molnar, Przemyslaw Biecek, Wojciech Samek
      Pages 13-38Open Access

    3. General Pitfalls of Model-Agnostic Interpretation Methods for Machine Learning Models

      • Christoph Molnar, Gunnar König, Julia Herbinger, Timo Freiesleben, Susanne Dandl, Christian A. Scholbeck et al.
      Pages 39-68Open Access

    4. CLEVR-X: A Visual Reasoning Dataset for Natural Language Explanations

      • Leonard Salewski, A. Sophia Koepke, Hendrik P. A. Lensch, Zeynep Akata
      Pages 69-88Open Access

  4. New Developments in Explainable AI

    1. Front Matter

      Pages 89-89
      PDF

    2. A Rate-Distortion Framework for Explaining Black-Box Model Decisions

      • Stefan Kolek, Duc Anh Nguyen, Ron Levie, Joan Bruna, Gitta Kutyniok
      Pages 91-115Open Access

    3. Explaining the Predictions of Unsupervised Learning Models

      • Grégoire Montavon, Jacob Kauffmann, Wojciech Samek, Klaus-Robert Müller
      Pages 117-138Open Access

    4. Towards Causal Algorithmic Recourse

      • Amir-Hossein Karimi, Julius von Kügelgen, Bernhard Schölkopf, Isabel Valera
      Pages 139-166Open Access

    6. XAI and Strategy Extraction via Reward Redistribution

      • Marius-Constantin Dinu, Markus Hofmarcher, Vihang P. Patil, Matthias Dorfer, Patrick M. Blies, Johannes Brandstetter et al.
      Pages 177-205Open Access

    7. Interpretable, Verifiable, and Robust Reinforcement Learning via Program Synthesis

      • Osbert Bastani, Jeevana Priya Inala, Armando Solar-Lezama
      Pages 207-228Open Access

    8. Interpreting and Improving Deep-Learning Models with Reality Checks

      • Chandan Singh, Wooseok Ha, Bin Yu
      Pages 229-254Open Access

    9. Beyond the Visual Analysis of Deep Model Saliency

      • Sarah Adel Bargal, Andrea Zunino, Vitali Petsiuk, Jianming Zhang, Vittorio Murino, Stan Sclaroff et al.
      Pages 255-269Open Access

    10. ECQ \(^{\text {x}}\) : Explainability-Driven Quantization for Low-Bit and Sparse DNNs

      • Daniel Becking, Maximilian Dreyer, Wojciech Samek, Karsten Müller, Sebastian Lapuschkin
      Pages 271-296Open Access

    11. A Whale’s Tail - Finding the Right Whale in an Uncertain World

      • Diego Marcos, Jana Kierdorf, Ted Cheeseman, Devis Tuia, Ribana Roscher
      Pages 297-313Open Access

  5. An Interdisciplinary Approach to Explainable AI

    1. Front Matter

      Pages 341-341
      PDF
Back to top

About this book

This is an open access book.

Statistical machine learning (ML) has triggered a renaissance of artificial intelligence (AI). While the most successful ML models, including Deep Neural Networks (DNN), have developed better predictivity, they have become increasingly complex, at the expense of human interpretability (correlation vs. causality). The field of explainable AI (xAI) has emerged with the goal of creating tools and models that are both predictive and interpretable and understandable for humans.

Explainable AI is receiving huge interest in the machine learning and AI research communities, across academia, industry, and government, and there is now an excellent opportunity to push towards successful explainable AI applications. This volume will help the research community to accelerate this process, to promote a more systematic use of explainable AI to improve models in diverse applications, and ultimately to better understand how current explainable AI methods need to be improved and what kind of theory of explainable AI is needed.

After overviews of current methods and challenges, the editors include chapters that describe new developments in explainable AI. The contributions are from leading researchers in the field, drawn from both academia and industry, and many of the chapters take a clear interdisciplinary approach to problem-solving. The concepts discussed include explainability, causability, and AI interfaces with humans, and the applications include image processing, natural language, law, fairness, and climate science.


Back to top

Keywords

  • Computer Science
  • Informatics
  • Conference Proceedings
  • Research
  • Applications
  • Open Access
Back to top

Editors and Affiliations

  • University of Natural Resources and Life Sciences Vienna, Vienna, Austria

    Andreas Holzinger

  • University of Alberta, Edmonton, Canada

    Randy Goebel

  • Princeton University, Princeton, USA

    Ruth Fong

  • Seoul National University, Seoul, Korea (Republic of)

    Taesup Moon

  • Technische Universität Berlin, Berlin, Germany

    Klaus-Robert Müller

  • Fraunhofer Heinrich Hertz Institute, Berlin, Germany

    Wojciech Samek

Back to top

Bibliographic Information

  • Book Title: xxAI - Beyond Explainable AI

  • Book Subtitle: International Workshop, Held in Conjunction with ICML 2020, July 18, 2020, Vienna, Austria, Revised and Extended Papers

  • Editors: Andreas Holzinger, Randy Goebel, Ruth Fong, Taesup Moon, Klaus-Robert Müller, Wojciech Samek

  • Series Title: Lecture Notes in Computer Science

  • DOI: https://doi.org/10.1007/978-3-031-04083-2

  • Publisher: Springer Cham

  • eBook Packages: Computer Science, Computer Science (R0)

  • Copyright Information: The Editor(s) (if applicable) and The Author(s) 2022

  • License: CC BY

  • Softcover ISBN: 978-3-031-04082-5Published: 17 April 2022

  • eBook ISBN: 978-3-031-04083-2Published: 16 April 2022

  • Series ISSN: 0302-9743

  • Series E-ISSN: 1611-3349

  • Edition Number: 1

  • Number of Pages: X, 397

  • Number of Illustrations: 10 b/w illustrations, 114 illustrations in colour

  • Topics: Artificial Intelligence, Machine Learning

Back to top
Softcover Book USD 49.99
Price excludes VAT (USA)
Learn about institutional subscriptions