A Survey on the Explainability of Supervised Machine Learning

DOI10.1613/jair.1.12228zbMath1497.68412arXiv2011.07876OpenAlexW3101981467MaRDI QIDQ5145841

Nadia Burkart, Marco F. Huber

Publication date: 22 January 2021

Published in: Journal of Artificial Intelligence Research (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/2011.07876

zbMATH Keywords

neural networksmachine learningknowledge discoveryrule learning

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Research exposition (monographs, survey articles) pertaining to computer science (68-02)

Related Items (7)

Witnesses for Answer Sets of Logic Programs ⋮ Explainable subgradient tree boosting for prescriptive analytics in operations management ⋮ Risk-aware shielding of partially observable Monte Carlo planning policies ⋮ Explaining black-box classifiers: properties and functions ⋮ A general framework for personalising post hoc explanations through user knowledge integration ⋮ Some models are useful, but how do we know which ones? Towards a unified Bayesian model taxonomy ⋮ Assessment of the influence of features on a classification problem: an application to COVID-19 patients

Uses Software

• UCI-ml
• C4.5
• t-SNE
• conformalInference
• shap
• Grad-CAM

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Predictive learning via rule ensembles
• Distribution-Free Predictive Inference For Regression
• Supersparse linear integer models for optimized medical scoring systems
• Prototype selection for interpretable classification
• Interpretable classifiers using rules and Bayesian analysis: building a better stroke prediction model
• Bayesian network classifiers
• Least angle regression. (With discussion)
• Greedy rule generation from discrete data and its use in neural network rule extraction
• Explanation in artificial intelligence: insights from the social sciences
• Very simple classification rules perform well on most commonly used datasets
• Comprehensible credit scoring models using rule extraction from support vector machines
• Ontology learning from text
• The Framing of Decisions and the Psychology of Choice
• Learning Domain Ontologies from Document Warehouses and Dedicated Web Sites
• Rule Extraction from Support Vector Machines
• Estimating Classification Uncertainty of Bayesian Decision Tree Technique on Financial Data
• Learning Optimized Risk Scores
• Definitions, methods, and applications in interpretable machine learning
• Discovering the Mysteries of Neural Networks
• A Statistically Precise and Relatively Simple Method of Estimating the Bioassay with Quantal Response, Based on the Logistic Function

This page was built for publication: A Survey on the Explainability of Supervised Machine Learning