Explainable and Transparent AI and Multi-Agent Systems [[electronic resource] ] : 5th International Workshop, EXTRAAMAS 2023, London, UK, May 29, 2023, Revised Selected Papers / / edited by Davide Calvaresi, Amro Najjar, Andrea Omicini, Reyhan Aydogan, Rachele Carli, Giovanni Ciatto, Yazan Mualla, Kary Främling

• Autore: Calvaresi Davide
• Pubblicazione: Cham : , : Springer Nature Switzerland : , : Imprint : Springer, , 2023
• Edizione: 1st ed. 2023.
• Descrizione fisica: 1 online resource (289 pages)
• Disciplina: 006.30285436
• Soggetto topico: Multiagent systems; Machine learning; Compilers (Computer programs); Natural language processing (Computer science); Computer science; Computers, Special purpose; Multiagent Systems; Machine Learning; Compilers and Interpreters; Natural Language Processing (NLP); Theory of Computation; Special Purpose and Application-Based Systems
• Altri autori: NajjarAmro OmiciniAndrea AydoganReyhan CarliRachele CiattoGiovanni MuallaYazan ämlingKary
• Nota di contenuto: Explainable Agents and multi-agent systems -- Mining and Validating Belief-based Agent Explanations -- Evaluating a mechanism for explaining BDI agent behaviour -- A General-Purpose Protocol for Multi-Agent based Explanations -- Dialogue Explanations for Rules-based AI Systems -- Estimating Causal Responsibility for Explaining Autonomous Behavior -- Explainable Machine Learning -- The Quarrel of Local Post-hoc Explainers for Moral Values Classification in Natural Language Processing -- Bottom-Up and Top-Down Workflows for Hypercube- and Clustering-based Knowledge Extractors -- Imperative Action Masking for Safe Exploration in Reinforcement Learning -- Reinforcement Learning in Cyclic Environmental Change for Non-Communicative Agents: A Theoretical Approach -- Inherently Interpretable Deep Reinforcement Learning through Online Mimicking -- Counterfactual, Contrastive, and Hierarchical Explanations with Contextual Importance and Utility -- Cross-domain applied XAI -- Explanation Generation via Decompositional Rules Extraction for Head and Neck Cancer Classification -- Metrics for Evaluating Explainable Recommender Systems -- Leveraging Imperfect Explanations for Plan Recognition Problems -- Reinterpreting Vulnerability to Tackle Deception in Principles-Based XAI for Human-Computer Interaction -- Using Cognitive Models and Wearables to Diagnose and Predict Dementia Patient Behaviour.
• Sommario/riassunto: This volume LNCS 14127 constitutes the refereed proceedings of the 5th International Workshop, EXTRAAMAS 2023, held in London, UK, in May 2023. The 15 full papers presented together with 1 short paper were carefully reviewed and selected from 26 submissions. The workshop focuses on Explainable Agents and multi-agent systems; Explainable Machine Learning; and Cross-domain applied XAI. .
• Titolo autorizzato: Explainable and Transparent AI and Multi-Agent Systems
• ISBN: 3-031-40878-0
• Formato: Materiale a stampa
• Livello bibliografico: Monografia
• Lingua di pubblicazione: Inglese
• Record Nr.: 996550561503316
• Lo trovi qui: Univ. di Salerno
• Serie: Lecture Notes in Artificial Intelligence, . 2945-9141 ; ; 14127