Modelling accuracy and trustworthiness of explaining agents

DOI10.1007/978-3-030-88708-7_19MaRDI QIDQ2148840zbMATH OpenOpenAlexFDO

Authors Alberto Termine, Giuseppe Primiero, Fabio Aurelio D'Asaro

Publication date 24 June 2022

Full work available at URL https://doi.org/10.1007/978-3-030-88708-7_19

zbMATH Keywords

accuracytrustworthinessexplainable AI

Mathematics Subject Classification ID

Logic in artificial intelligence (68T27)

Recommendations

• Descriptive accuracy in explanations: the case of probabilistic classifiers
• Why bad coffee? Explaining BDI agent behaviour with valuings
• Foundations of explanations as model reconciliation
• Using state abstractions to compute personalized contrastive explanations for AI agent behavior
• Artificial explanations: The epistemological interpretation of explanation in AI

Cites work

• scientific article; zbMATH DE number 5585443 (Why is no real title available?)
• A computationally grounded, weighted doxastic logic
• A logic for reasoning about time and reliability
• Interpretable machine learning: fundamental principles and 10 grand challenges
• mcmas: A Model Checker for Multi-agent Systems

Cited in

(2)

• Descriptive accuracy in explanations: the case of probabilistic classifiers
• A possible worlds semantics for trustworthy non-deterministic computations

Describes a project that uses

Uses Software

• PRMLT
• MCMAS

This page was built for publication: Modelling accuracy and trustworthiness of explaining agents

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2148840)