xxAI -- beyond explainable AI : International Workshop, held in conjunction with ICML 2020, July 18, 2020, Vienna, Austria, Revised and extended papers

xxAI -- beyond explainable AI International Workshop, held in conjunction with ICML 2020, July 18, 2020, Vienna, Austria, Revised and extended papers

This is an open access book. Statistical machine learning (ML) has triggered a renaissance of artificial intelligence (AI). While the most successful ML models, including Deep Neural Networks (DNN), have developed better predictivity, they have become increasingly complex, at the expense of human in...

Descripción completa

Detalles Bibliográficos
Autores Corporativos: xxAI (Workshop) (-), International Conference on Machine Learning
Otros Autores: Holzinger, Andreas, editor (editor), Goebel, Randy, editor, Fong, Ruth, editor, Moon, Taesup, editor, Müller, Klaus-Robert, editor, Samek, Wojciech, editor
Formato: Libro electrónico
Idioma:Inglés
Publicado: Cham, Switzerland : Springer 2022.
Colección:Springer open access eBooks.
Lecture notes in artificial intelligence.
Lecture notes in computer science ; 13200.
LNCS sublibrary, SL 7, Artificial intelligence.
Acceso en línea:Conectar con la versión electrónica
Ver en Universidad de Navarra:https://innopac.unav.es/record=b47265693*spi
Tabla de Contenidos:
  • Editorial
  • xxAI - Beyond explainable Artificial Intelligence
  • Current Methods and Challenges
  • Explainable AI Methods - A Brief Overview
  • Challenges in Deploying Explainable Machine Learning
  • Methods for Machine Learning Models
  • CLEVR-X: A Visual Reasoning Dataset for Natural Language Explanations
  • New Developments in Explainable AI
  • A Rate-Distortion Framework for Explaining Black-box Model Decisions
  • Explaining the Predictions of Unsupervised Learning Models
  • Towards Causal Algorithmic Recourse
  • Interpreting Generative Adversarial Networks for Interactive Image Generation
  • XAI and Strategy Extraction via Reward Redistribution
  • Interpretable, Verifiable, and Robust Reinforcement Learning via Program Synthesis
  • Interpreting and improving deep-learning models with reality checks
  • Beyond the Visual Analysis of Deep Model Saliency
  • ECQ2̂: Quantization for Low-Bit and Sparse DNNs
  • A whale's tail - Finding the right whale in an uncertain world
  • Explainable Artificial Intelligence in Meteorology and Climate Science: Model fine-tuning, calibrating trust and learning new science
  • An Interdisciplinary Approach to Explainable AI.-Varieties of AI Explanations under the Law - From the GDPR to the AIA, and beyond
  • Towards Explainability for AI Fairness
  • Logic and Pragmatics in AI Explanation.

Ejemplares similares