Limit search to available items
Book Cover
Author EXTRAAMAS (Workshop) (1st : 2019 : Montréal, Québec)

Title Explainable, transparent autonomous agents and multi-agent systems : first International Workshop, EXTRAAMAS 2019, Montreal, QC, Canada, May 13-14, 2019, Revised selected papers / Davide Calvaresi, Amro Najjar, Michael Schumacher, Kary Främling (eds.)
Published Cham, Switzerland : Springer, 2019
Online access available from:
Springer eBooks    View Resource Record  


Description 1 online resource (x, 221 pages) : illustrations (some color)
Series LNCS sublibrary. SL 7, Artificial intelligence
Lecture notes in artificial intelligence
Lecture notes in computer science ; 11763
LNCS sublibrary. SL 7, Artificial intelligence
Lecture notes in computer science ; 11763
Lecture notes in computer science. Lecture notes in artificial intelligence.
Contents Intro; Preface; Organization; Contents; Explanation and Transparency; Towards a Transparent Deep Ensemble Method Based on Multiagent Argumentation; 1 Introduction; 2 State of Art; 2.1 Ensemble Method; 2.2 Argumentation in ML; 2.3 Explainable Intelligent Systems; 3 Method; 3.1 Arguments Extraction Phase; 3.2 Multiagent Argumentation Phase; 4 Case Study; 4.1 Data Description; 4.2 Scenarios Illustration; 5 Experimentation; 6 Conclusion; References; Effects of Agents' Transparency on Teamwork; 1 Introduction; 2 Related Work; 3 Research Design and Methods; 4 Objective and Hypothesis
1 Introduction2 Background; 2.1 Behavioral Economics and Multi-agent Systems; 2.2 Machine Theory of Mind; 2.3 Explainable Artificial Intelligence (XAI) and Explainable Agents; 3 A Taxonomy of Goals for Sympathetic Actions; 4 Ways to Explain Sympathetic Actions; 5 Towards an Empirical Assessment; 5.1 Study Design; 5.2 Data Collection and Analysis; 5.3 Results; 5.4 Interpretation; 6 Discussion; 6.1 Sympathetic Actions of Learning Agents; 6.2 Limitations; 6.3 Future Work; 7 Conclusion; References; Conversational Interfaces for Explainable AI: A Human-Centred Approach; 1 Introduction
2 Designing a Wizard of Oz Experiment3 User Behaviour in Conversational Interfaces for XAI; 3.1 Users' Question Formulation; 3.2 Strategies of Interaction; 4 Implications for the Implementation of CIs; 4.1 The Information Privacy Trade-Off; 4.2 The Necessity of Repair Questions; 4.3 Question Intents for Better Machine Understanding; 5 Related Work; 6 Discussion; 7 Conclusion and Outlook; References; Opening the Black Box; Explanations of Black-Box Model Predictions by Contextual Importance and Utility; Abstract; 1 Introduction; 2 Background; 3 State of the Art
4 Contextual Importance and Contextual Utility5 Examples of CI and CU Method to Extract Explanation for Linear and Non-linear Models; 5.1 Visual Explanations for Car Selection Using CI and CU Method; 5.2 Explaining Iris Flower Classification Using CI and CU Method; 6 Discussion; 7 Conclusion; Acknowledgment; References; Explainable Artificial Intelligence Based Heat Recycler Fault Detection in Air Handling Unit; 1 Introduction; 2 Previous Work; 3 Theoretical Background; 3.1 Heat Recycler Unit; 3.2 Support Vector Machine; 3.3 Neural Networks; 3.4 Explainable Artificial Intelligence
4.1 Materials and Methods4.2 Metrics and Data Collection; 4.3 Procedure; 5 User Study; 5.1 Participants; 5.2 Data Analysis; 6 Discussion; 7 Conclusions; References; Explainable Robots; Explainable Multi-Agent Systems Through Blockchain Technology; 1 Introduction; 2 Background; 2.1 Trust; 2.2 Explainability; 2.3 Blockchain Technology; 3 Application Domains; 4 Challenges; 4.1 RC Scenarios; 4.2 LT Scenarios; 5 Proposed Solution; 5.1 RC; 5.2 LT; 6 Explainability and BCT: The UAVs Package Delivery Use Case; 7 Discussion; 8 Conclusions; References; Explaining Sympathetic Actions of Rational Agents
Summary This book constitutes the proceedings of the First International Workshop on Explainable, Transparent Autonomous Agents and Multi-Agent Systems, EXTRAAMAS 2019, held in Montreal, Canada, in May 2019. The 12 revised and extended papers presented were carefully selected from 23 submissions. They are organized in topical sections on explanation and transparency; explainable robots; opening the black box; explainable agent simulations; planning and argumentation; explainable AI and cognitive science. -- Provided by publisher
Notes Includes author index
Online resource; title from PDF title page (SpringerLink, viewed September 24, 2019)
Subject Intelligent agents (Computer software) -- Congresses.
Intelligent agents (Computer software)
Genre/Form Conference papers and proceedings.
Form Electronic book
Author Calvaresi, Davide, editor.
Främling, Kary, editor.
Najjar, Amro, editor.
Schumacher, Michael, editor
ISBN 3030303918
Other Titles EXTRAAMAS 2019