A survey on the explainability of supervised machine learning
From MaRDI portal
Abstract: Predictions obtained by, e.g., artificial neural networks have a high accuracy but humans often perceive the models as black boxes. Insights about the decision making are mostly opaque for humans. Particularly understanding the decision making in highly sensitive areas such as healthcare or fifinance, is of paramount importance. The decision-making behind the black boxes requires it to be more transparent, accountable, and understandable for humans. This survey paper provides essential definitions, an overview of the different principles and methodologies of explainable Supervised Machine Learning (SML). We conduct a state-of-the-art survey that reviews past and recent explainable SML approaches and classifies them according to the introduced definitions. Finally, we illustrate principles by means of an explanatory case study and discuss important future directions.
Recommendations
- Explainable deep learning: a field guide for the uninitiated
- Definitions, methods, and applications in interpretable machine learning
- How to explain individual classification decisions
- Towards analogy-based explanations in machine learning
- Local interpretation of supervised learning models based on high dimensional model representation
Cites work
- A Bayesian framework for learning rule sets for interpretable classification
- A Statistically Precise and Relatively Simple Method of Estimating the Bioassay with Quantal Response, Based on the Logistic Function
- Bayesian network classifiers
- Comprehensible credit scoring models using rule extraction from support vector machines
- Definitions, methods, and applications in interpretable machine learning
- Discovering the Mysteries of Neural Networks
- Distribution-free predictive inference for regression
- Estimating Classification Uncertainty of Bayesian Decision Tree Technique on Financial Data
- Explanation in artificial intelligence: insights from the social sciences
- Greedy rule generation from discrete data and its use in neural network rule extraction
- How to explain individual classification decisions
- scientific article; zbMATH DE number 2086056 (Why is no real title available?)
- scientific article; zbMATH DE number 817981 (Why is no real title available?)
- scientific article; zbMATH DE number 845714 (Why is no real title available?)
- scientific article; zbMATH DE number 7238293 (Why is no real title available?)
- Interpretable classifiers using rules and Bayesian analysis: building a better stroke prediction model
- Learning domain ontologies from document warehouses and dedicated web sites
- Learning optimized risk scores
- Least angle regression. (With discussion)
- Ontology learning from text: a look back and into the future
- Predictive learning via rule ensembles
- Prototype selection for interpretable classification
- Rule Extraction from Support Vector Machines
- Rule extraction from support vector machines: an overview of issues and application in credit scoring
- Supersparse linear integer models for optimized medical scoring systems
- The framing of decisions and the psychology of choice
- Very simple classification rules perform well on most commonly used datasets
- Visualizing data using t-SNE
Cited in
(38)- Explicative deep learning with probabilistic formal concepts in a natural language processing task
- Towards analogy-based explanations in machine learning
- Beneficial and harmful explanatory machine learning
- Knowledge graphs as tools for explainable machine learning: a survey
- Interpretable machine learning: fundamental principles and 10 grand challenges
- Assessment of the influence of features on a classification problem: an application to COVID-19 patients
- Explainable models of credit losses
- Assessing heuristic machine learning explanations with model counting
- Explanation in artificial intelligence: insights from the social sciences
- How to explain individual classification decisions
- scientific article; zbMATH DE number 1301669 (Why is no real title available?)
- Explainable deep learning: a field guide for the uninitiated
- L. A. Zadeh, the visionary in explainable artificial intelligence
- Definitions, methods, and applications in interpretable machine learning
- Witnesses for Answer Sets of Logic Programs
- The explanation game: a formal framework for interpretable machine learning
- Explainable subgradient tree boosting for prescriptive analytics in operations management
- Risk-aware shielding of partially observable Monte Carlo planning policies
- Explainable generalized additive neural networks with independent neural network training
- SLISEMAP: supervised dimensionality reduction through local explanations
- Explaining black-box classifiers: properties and functions
- A general framework for personalising post hoc explanations through user knowledge integration
- Considerations when learning additive explanations for black-box models
- Some models are useful, but how do we know which ones? Towards a unified Bayesian model taxonomy
- Explainable ensemble trees
- Explaining and predicting customer churn by monotonic rules induced from ordinal data
- Synergies between machine learning and reasoning -- an introduction by the Kay R. Amel group
- Selecting fast algorithms for the capacitated vehicle routing problem with machine learning techniques
- Explaining random forest and XGBoost with shallow decision trees by co-clustering feature importance
- Spatio-causal patterns of sample growth
- Efficient XAI: a low-cost data reduction approach to SHAP interpretability
- S-SIRUS: an explainability algorithm for spatial regression random forest
- OccPoIs: points of interest based on neural network's key recovery in side-channel analysis through occlusion
- Decision trees with short explainable rules
- Automatic algorithm selection for pseudo-Boolean optimization with given computational time limits
- Distributional refinement network: distributional forecasting via deep learning
- General supervised learning framework for open world classification
- Empirical Bayes fairness in linear regression
This page was built for publication: A survey on the explainability of supervised machine learning
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5145841)
