Explainable Artificial Intelligence

TRAMA

This four-volume set constitutes the refereed proceedings of the Second World Conference on Explainable Artificial Intelligence, xAI 2024, held in Valletta, Malta, during July 17-19, 2024.  The 95 full papers presented were carefully reviewed and selected from 204 submissions. The conference papers are organized in topical sections on: Part I - intrinsically interpretable XAI and concept-based global explainability; generative explainable AI and verifiability; notion, metrics, evaluation and benchmarking for XAI. Part II - XAI for graphs and computer vision; logic, reasoning, and rule-based explainable AI; model-agnostic and statistical methods for eXplainable AI. Part III - counterfactual explanations and causality for eXplainable AI; fairness, trust, privacy, security, accountability and actionability in eXplainable AI. Part IV - explainable AI in healthcare and computational neuroscience; explainable AI for improved human-computer interaction and software engineering for explainability; applications of explainable artificial intelligence.

SOMMARIO

.- Intrinsically interpretable XAI and concept-based global explainability. .- Seeking Interpretability and Explainability in Binary Activated Neural Networks. .- Prototype-based Interpretable Breast Cancer Prediction Models: Analysis and Challenges. .- Evaluating the Explainability of Attributes and Prototypes for a Medical Classification Model. .- Revisiting FunnyBirds evaluation framework for prototypical parts networks. .- CoProNN: Concept-based Prototypical Nearest Neighbors for Explaining Vision Models. .- Unveiling the Anatomy of Adversarial Attacks: Concept-based XAI Dissection of CNNs. .- AutoCL: AutoML for Concept Learning. .- Locally Testing Model Detections for Semantic Global Concepts. .- Knowledge graphs for empirical concept retrieval. .- Global Concept Explanations for Graphs by Contrastive Learning. .- Generative explainable AI and verifiability. .- Augmenting XAI with LLMs: A Case Study in Banking Marketing Recommendation. .- Generative Inpainting for Shapley-Value-Based Anomaly Explanation. .- Challenges and Opportunities in Text Generation Explainability. .- NoNE Found: Explaining the Output of Sequence-to-Sequence Models when No Named Entity is Recognized. .- Notion, metrics, evaluation and benchmarking for XAI. .- Benchmarking Trust: A Metric for Trustworthy Machine Learning. .- Beyond the Veil of Similarity: Quantifying Semantic Continuity in Explainable AI. .- Conditional Calibrated Explanations: Finding a Path between Bias and Uncertainty. .- Meta-evaluating stability measures: MAX-Sensitivity & AVG-Senstivity. .- Xpression: A unifying metric to evaluate Explainability and Compression of AI models. .- Evaluating Neighbor Explainability for Graph Neural Networks. .- A Fresh Look at Sanity Checks for Saliency Maps. .- Explainability, Quantified: Benchmarking XAI techniques. .- BEExAI: Benchmark to Evaluate Explainable AI. .- Associative Interpretability of Hidden Semantics with Contrastiveness Operators in Face Classification tasks.

ALTRE INFORMAZIONI

• Condizione: Nuovo
• ISBN: 9783031637865
• Collana: Communications in Computer and Information Science
• Dimensioni: 235 x 155 mm
• Formato: Brossura
• Illustration Notes: XVII, 494 p. 143 illus., 137 illus. in color.
• Pagine Arabe: 494
• Pagine Romane: xvii