Interpretable and explainable machine learning: A methods-centric overview with concrete examples. Marcinkevičs, R. & Vogt, J. E. WIREs Data Mining and Knowledge Discovery, n/a(n/a):e1493. _eprint: https://onlinelibrary.wiley.com/doi/pdf/10.1002/widm.1493![Interpretable and explainable machine learning: A methods-centric overview with concrete examples [link]](https://bibbase.org/img/filetypes/link.svg "link")
Paper doi abstract bibtex Interpretability and explainability are crucial for machine learning (ML) and statistical applications in medicine, economics, law, and natural sciences and form an essential principle for ML model design and development. Although interpretability and explainability have escaped a precise and universal definition, many models and techniques motivated by these properties have been developed over the last 30 years, with the focus currently shifting toward deep learning. We will consider concrete examples of state-of-the-art, including specially tailored rule-based, sparse, and additive classification models, interpretable representation learning, and methods for explaining black-box models post hoc. The discussion will emphasize the need for and relevance of interpretability and explainability, the divide between them, and the inductive biases behind the presented “zoo” of interpretable models and explanation methods. This article is categorized under: Fundamental Concepts of Data and Knowledge \textgreater Explainable AI Technologies \textgreater Machine Learning Commercial, Legal, and Ethical Issues \textgreater Social Considerations
@article{marcinkevics_interpretable_nodate,
title = {Interpretable and explainable machine learning: {A} methods-centric overview with concrete examples},
volume = {n/a},
issn = {1942-4795},
shorttitle = {Interpretable and explainable machine learning},
url = {https://onlinelibrary.wiley.com/doi/abs/10.1002/widm.1493},
doi = {10.1002/widm.1493},
abstract = {Interpretability and explainability are crucial for machine learning (ML) and statistical applications in medicine, economics, law, and natural sciences and form an essential principle for ML model design and development. Although interpretability and explainability have escaped a precise and universal definition, many models and techniques motivated by these properties have been developed over the last 30 years, with the focus currently shifting toward deep learning. We will consider concrete examples of state-of-the-art, including specially tailored rule-based, sparse, and additive classification models, interpretable representation learning, and methods for explaining black-box models post hoc. The discussion will emphasize the need for and relevance of interpretability and explainability, the divide between them, and the inductive biases behind the presented “zoo” of interpretable models and explanation methods. This article is categorized under: Fundamental Concepts of Data and Knowledge {\textgreater} Explainable AI Technologies {\textgreater} Machine Learning Commercial, Legal, and Ethical Issues {\textgreater} Social Considerations},
language = {en},
number = {n/a},
urldate = {2023-03-08},
journal = {WIREs Data Mining and Knowledge Discovery},
author = {Marcinkevičs, Ričards and Vogt, Julia E.},
note = {\_eprint: https://onlinelibrary.wiley.com/doi/pdf/10.1002/widm.1493},
keywords = {explainability, interpretability, machine learning, neural networks},
pages = {e1493},
}
Downloads: 0
{"_id":"QwZKsqibgxZ2GXutK","bibbaseid":"marcinkevis-vogt-interpretableandexplainablemachinelearningamethodscentricoverviewwithconcreteexamples","author_short":["Marcinkevičs, R.","Vogt, J. E."],"bibdata":{"bibtype":"article","type":"article","title":"Interpretable and explainable machine learning: A methods-centric overview with concrete examples","volume":"n/a","issn":"1942-4795","shorttitle":"Interpretable and explainable machine learning","url":"https://onlinelibrary.wiley.com/doi/abs/10.1002/widm.1493","doi":"10.1002/widm.1493","abstract":"Interpretability and explainability are crucial for machine learning (ML) and statistical applications in medicine, economics, law, and natural sciences and form an essential principle for ML model design and development. Although interpretability and explainability have escaped a precise and universal definition, many models and techniques motivated by these properties have been developed over the last 30 years, with the focus currently shifting toward deep learning. We will consider concrete examples of state-of-the-art, including specially tailored rule-based, sparse, and additive classification models, interpretable representation learning, and methods for explaining black-box models post hoc. The discussion will emphasize the need for and relevance of interpretability and explainability, the divide between them, and the inductive biases behind the presented “zoo” of interpretable models and explanation methods. This article is categorized under: Fundamental Concepts of Data and Knowledge \\textgreater Explainable AI Technologies \\textgreater Machine Learning Commercial, Legal, and Ethical Issues \\textgreater Social Considerations","language":"en","number":"n/a","urldate":"2023-03-08","journal":"WIREs Data Mining and Knowledge Discovery","author":[{"propositions":[],"lastnames":["Marcinkevičs"],"firstnames":["Ričards"],"suffixes":[]},{"propositions":[],"lastnames":["Vogt"],"firstnames":["Julia","E."],"suffixes":[]}],"note":"_eprint: https://onlinelibrary.wiley.com/doi/pdf/10.1002/widm.1493","keywords":"explainability, interpretability, machine learning, neural networks","pages":"e1493","bibtex":"@article{marcinkevics_interpretable_nodate,\n\ttitle = {Interpretable and explainable machine learning: {A} methods-centric overview with concrete examples},\n\tvolume = {n/a},\n\tissn = {1942-4795},\n\tshorttitle = {Interpretable and explainable machine learning},\n\turl = {https://onlinelibrary.wiley.com/doi/abs/10.1002/widm.1493},\n\tdoi = {10.1002/widm.1493},\n\tabstract = {Interpretability and explainability are crucial for machine learning (ML) and statistical applications in medicine, economics, law, and natural sciences and form an essential principle for ML model design and development. Although interpretability and explainability have escaped a precise and universal definition, many models and techniques motivated by these properties have been developed over the last 30 years, with the focus currently shifting toward deep learning. We will consider concrete examples of state-of-the-art, including specially tailored rule-based, sparse, and additive classification models, interpretable representation learning, and methods for explaining black-box models post hoc. The discussion will emphasize the need for and relevance of interpretability and explainability, the divide between them, and the inductive biases behind the presented “zoo” of interpretable models and explanation methods. This article is categorized under: Fundamental Concepts of Data and Knowledge {\\textgreater} Explainable AI Technologies {\\textgreater} Machine Learning Commercial, Legal, and Ethical Issues {\\textgreater} Social Considerations},\n\tlanguage = {en},\n\tnumber = {n/a},\n\turldate = {2023-03-08},\n\tjournal = {WIREs Data Mining and Knowledge Discovery},\n\tauthor = {Marcinkevičs, Ričards and Vogt, Julia E.},\n\tnote = {\\_eprint: https://onlinelibrary.wiley.com/doi/pdf/10.1002/widm.1493},\n\tkeywords = {explainability, interpretability, machine learning, neural networks},\n\tpages = {e1493},\n}\n\n","author_short":["Marcinkevičs, R.","Vogt, J. E."],"key":"marcinkevics_interpretable_nodate","id":"marcinkevics_interpretable_nodate","bibbaseid":"marcinkevis-vogt-interpretableandexplainablemachinelearningamethodscentricoverviewwithconcreteexamples","role":"author","urls":{"Paper":"https://onlinelibrary.wiley.com/doi/abs/10.1002/widm.1493"},"keyword":["explainability","interpretability","machine learning","neural networks"],"metadata":{"authorlinks":{}}},"bibtype":"article","biburl":"https://bibbase.org/zotero/mh_lenguyen","dataSources":["iwKepCrWBps7ojhDx"],"keywords":["explainability","interpretability","machine learning","neural networks"],"search_terms":["interpretable","explainable","machine","learning","methods","centric","overview","concrete","examples","marcinkevičs","vogt"],"title":"Interpretable and explainable machine learning: A methods-centric overview with concrete examples","year":null}