How to explain individual classification decisions

zbMATH Open1242.62049MaRDI QIDQ2896115FDOQ2896115

Authors: David Baehrens, Timon Schroeter, Stefan Harmeling, Motoaki Kawanabe, Katja Hansen, Klaus-Robert Müller 

Publication date: 13 July 2012

Published in: Journal of Machine Learning Research (JMLR) (Search for Journal in Brave)

Full work available at URL: http://www.jmlr.org/papers/v11/baehrens10a.html

Recommendations

• An efficient explanation of individual classifications using game theory
• scientific article; zbMATH DE number 1934575
• A survey on the explainability of supervised machine learning
• On the reasons behind decisions
• Interpretation of black-box predictive models

zbMATH Keywords

kernel methodsnonlinearblack box modelmutagenicity

Mathematics Subject Classification ID

Classification and discrimination; cluster analysis (statistical aspects) (62H30) Learning and adaptive systems in artificial intelligence (68T05)

Cited In (36)

• Explaining individual predictions when features are dependent: more accurate approximations to Shapley values
• Sharing hash codes for multiple purposes
• Foundations of fine-grained explainability
• SIRUS: stable and interpretable RUle set for classification
• Explanation in artificial intelligence: insights from the social sciences
• On the reasons behind decisions
• Learning Optimal Decision Sets and Lists with SAT
• A comparison of instance-level counterfactual explanation algorithms for behavioral and textual data: SEDC, LIME-C and SHAP-C
• A framework for inherently interpretable optimization models
• Explicative deep learning with probabilistic formal concepts in a natural language processing task
• Comments on ``Data science, big data and statistics
• Assessing heuristic machine learning explanations with model counting
• Title not available (Why is that?)
• Learning with rationales for document classification
• Title not available (Why is that?)
• Describing the result of a classifier to the end-user: geometric-based sensitivity
• Model-agnostic explanations for survival prediction models
• Interpretation of black-box predictive models
• An efficient explanation of individual classifications using game theory
• Scrutinizing XAI using linear ground-truth data with suppressor variables
• Variable importance evaluation with personalized odds ratio for machine learning model interpretability with applications to electronic health records-based mortality prediction
• A survey on the explainability of supervised machine learning
• Explainable deep learning: a field guide for the uninitiated
• Conclusive local interpretation rules for random forests
• Rationalizing predictions by adversarial information calibration
• SLISEMAP: supervised dimensionality reduction through local explanations
• Temporal inductive path neural network for temporal knowledge graph reasoning
• Explaining AI decisions using efficient methods for learning sparse Boolean formulae
• Constrained dynamics, stochastic numerical methods and the modeling of complex systems. Abstracts from the workshop held May 26--31, 2024
• Backtransformation: a new representation of data processing chains with a scalar decision function
• Feature necessity \& relevancy in ML classifier explanations
• A Symbolic Approach for Counterfactual Explanations
• The LRP toolbox for artificial neural networks
• Considerations when learning additive explanations for black-box models
• A new class of explanations for classifiers with non-binary features
• Explaining machine learning models using entropic variable projection

This page was built for publication: How to explain individual classification decisions

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2896115)