Explainable and Transparent AI and Multi-Agent Systems
Springer International Publishing (Verlag)
978-3-031-40877-9 (ISBN)
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.
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.
| Erscheinungsdatum | 06.09.2023 |
|---|---|
| Reihe/Serie | Lecture Notes in Artificial Intelligence | Lecture Notes in Computer Science |
| Zusatzinfo | XII, 281 p. 69 illus., 47 illus. in color. |
| Verlagsort | Cham |
| Sprache | englisch |
| Maße | 155 x 235 mm |
| Gewicht | 451 g |
| Themenwelt | Informatik ► Theorie / Studium ► Compilerbau |
| Informatik ► Theorie / Studium ► Künstliche Intelligenz / Robotik | |
| Schlagworte | Artificial Intelligence • Compilers and interpreters • Computing most probable explanation • Knowledge Representation and Reasoning • Law • machine learning • Multiagent Systems • Natural Language Processing (NLP) • rule learning • Social and behavioral sciences • Special purpose and application-based systems • Theory of Computation |
| ISBN-10 | 3-031-40877-2 / 3031408772 |
| ISBN-13 | 978-3-031-40877-9 / 9783031408779 |
| Zustand | Neuware |
| Haben Sie eine Frage zum Produkt? |
aus dem Bereich
