This book constitutes the refereed proceedings of the 4th International Workshop on Explainable and Transparent AI and Multi-Agent Systems, EXTRAAMAS 2022, held virtually during May 9 10, 2022.
The 14 full papers included in this book were carefully reviewed and selected from 25 submissions. They were organized in topical sections as follows: explainable machine learning; explainable neuro-symbolic AI; explainable agents; XAI measures and metrics; and AI & law.
Inhaltsverzeichnis
Explainable Machine Learning
. - Evaluation of importance estimators in deep learning classifiers for Computed Tomography. - Integration of local and global features explanation with global rules extraction and generation tools. - ReCCoVER: Detecting Causal Confusion for Explainable Reinforcement Learning. - Smartphone based grape leaf disease diagnosis and remedial system Assisted with explanations. -
Explainable Neuro-Symbolic AI
. - Recent Neural-Symbolic Approaches to ILP Based on Templates. - On the Design of PSyKI: a Platform for Symbolic Knowledge Injection into Sub-Symbolic Predictors. -
Explainable Agents
. - The Mirror Agent Model: a Bayesian Architecture for Interpretable Agent Behavior. - Semantic Web-based Interoperability for Intelligent Agents with PsyKE. - Case-based reasoning via comparing the strength order of features. -
XAI Measures and Metrics
. - Explainability Metrics and Properties for Counterfactual Explanation Methods. - The use of partial order relations and measure theory in developing objective measures of explainability. -
AI & Law
. - An Evaluation of Methodologies for Legal Formalization. - Risk and Exposure of XAI in Persuasion and Argumentation: The case of Manipulation. - Requirements for Tax XAI under Constitutional Principles and Human Rights.
