[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-117732-en":3,"doc-seo-117732-105":30,"detail-sidebar-cat-0-en-105":91},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":4,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":27,"seo_description":14,"update_tm":28,"read_time":29},117732,1099513958607,"Jiven","https://ap-avatar.wpscdn.com/avatar/100002390cf8733938c?x-image-process=image/resize,m_fixed,w_180,h_180&k=1778829742770036399",8,"Research & Report","Interpretability and Explainability - A Machine Learning Zoo Mini-tour","Review focused on designing interpretable and explainable machine learning models, highlighting that the field lacks a single universal definition. It distinguishes interpretability from explainability and maps these directions through concrete state-of-the-art examples. The primer targets general ML readers and covers interpretation beyond common baselines like logistic regression or random-forest variable importance. It summarizes motivations and desiderata such as trust, causality, robustness, fairness, and privacy.","arXiv :2012 .0 1805v 1 [ cs .LG] 3 Dec 2020  \nInterpretability and Explainability: A Machine Learning Zoo Mini-tour  \nRiards Marcinkevis􀀌 , Julia E. Vogt  \nETH Zürich, Department of Computer Science,  \nInstitute for Machine Learning  \nDecember, 2020  \nIn this review, we examine the problem of designing interpretable and explainable machine learning models. Interpretability and explainability lie at the core of many machine learning and statistical applications in medicine, economics, law, and natural sciences. Although interpretability and explainability have escaped a clear universal de􀀌nition, many techniques motivated by these properties have been developed over the recent 30 years with the focus currently shifting towards deep learning methods. In this review, we emphasise the divide between interpretability and explainability and illustrate these two different research directions with concrete examples of the state-of-the-art. The review is intended for a general machine learning audience with interest in exploring the problems of interpretation and explanation beyond logistic regression or random forest variable importance. This work is not an exhaustive literature survey, but rather a primer focusing selectively on certain lines of research which the authors found interesting or informative.  \n1 Interpretability, Explainability, and Intelligibility  \nInterpretable and explainable ML techniques emerge from a need to design intelligible machine learning systems, i.e. ones that can be comprehended by a human mind, and to understand and explain predictions made by opaque models, such as deep neural networks [1] or gradient boosting machines [2, 3] . The early research on interpretable machine learning dates back to the 1990s [4] and often does not refer to terms like “interpretability” or “explainability”, not to mention that many classical statistical models can be deemed interpretable.  \nIn general, there is no agreement within the ML community on the de􀀌nition of interpretability and the task of interpretation [5, 6] . For example, Doshi-Velez and Kim de􀀌ne interpretability of ML systems as “the ability to explain or to present in understandable terms to a human” [5] . This de􀀌nition clearly lacks mathematical rigour [6] . Nevertheless, the notion of interpretability often depends on the domain of application [4] and the target explainee [7], i.e. the recipient of interpretations and explanations, therefore, an all-purpose de􀀌nition might be infeasible [4] or unnecessary. Other terms that are synonymous to interpretability and also appear in the ML literature are “intelligibility” [8, 9] and “understandability” [6] . These concepts are often used interchangeably.  \nYet another term prevalent in the literature is “explainability”, giving rise to the direction of explainable arti􀀌cial intelligence (XAI) [10] . This concept is closely tied with interpretability; and many authors do not differentiate between the two [7] . Doshi-Velez and Kim [5] provide a de􀀌nition of explanation that originates from psychology: “explanations are... the currency in which we exchange beliefs”. In [4], Rudin draws a clear line between interpretable and explainable ML: interpretable ML focuses on designing models that are inherently interpretable; whereas explainable ML tries to provide post hoc explanations for existing black box models, i.e. models that are incomprehensible to humans or are proprietary [4] . For the sake of convenience, in this review, we adhere to the distinction proposed by Rudin [4] . In [6], Lipton stresses the difference in questions the two families of techniques try to address: interpretability raises the question “How does the model work?”; whereas explanation methods try to answer “What else can the model tell me?”.  \n􀀌 [ricards.marcinkevics@inf.ethz.ch](ricards.marcinkevics@inf.ethz.ch)  \nSince there is no general de􀀌nition of either interpretability or explainability, researchers have elicited various desiderata, d","cbCaislSXUmYbfae","https://ap.wps.com/l/cbCaislSXUmYbfae","pdf",398433,1,24,"English","en",105,"# Interpretability, Explainability, and Intelligibility\n## Definitions and terminology\n## Goals and desiderata for interpretability","[{\"question\":\"Why do researchers distinguish interpretability from explainability in machine learning?\",\"answer\":\"Interpretability focuses on models that are inherently understandable, while explainability emphasizes post hoc explanations for existing black-box models. The review follows this separation to clarify two research directions.\"},{\"question\":\"Is there a universal definition of interpretability or explainability?\",\"answer\":\"No. The ML community does not agree on a single formal definition, and proposed definitions often lack mathematical rigor. The concept also varies with the application domain and intended explainee.\"},{\"question\":\"What motivates interpretability-related techniques besides model understanding?\",\"answer\":\"The review summarizes goals such as building trust, supporting causal reasoning, improving robustness and transferability under domain shifts, detecting fairness issues, and addressing privacy concerns. These motivations can require techniques that reflect underlying model behavior faithfully.\"}]","Interpretability and Explainability - A Machine Learning Zoo Mini-tour | PDF",1785679263,60,{"code":4,"msg":31,"data":32},"ok",{"site_id":24,"language":23,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":28},"interpretability-and-explainability-a-machine-learning-zoo-mini-tour","",{"@graph":36,"@context":85},[37,54,68],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,51],{"item":41,"name":42,"@type":43,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":47},"https://docshare.wps.com/document/","Document",2,{"item":49,"name":12,"@type":43,"position":50},"https://docshare.wps.com/document/research-report/",3,{"item":52,"name":13,"@type":43,"position":53},"https://docshare.wps.com/document/interpretability-and-explainability-a-machine-learning-zoo-mini-tour/117732/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":62,"encodingFormat":61,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-02",true,{"@type":65,"interactionType":66,"userInteractionCount":4},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"Why do researchers distinguish interpretability from explainability in machine learning?","Question",{"text":75,"@type":76},"Interpretability focuses on models that are inherently understandable, while explainability emphasizes post hoc explanations for existing black-box models. The review follows this separation to clarify two research directions.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"Is there a universal definition of interpretability or explainability?",{"text":80,"@type":76},"No. The ML community does not agree on a single formal definition, and proposed definitions often lack mathematical rigor. The concept also varies with the application domain and intended explainee.",{"name":82,"@type":73,"acceptedAnswer":83},"What motivates interpretability-related techniques besides model understanding?",{"text":84,"@type":76},"The review summarizes goals such as building trust, supporting causal reasoning, improving robustness and transferability under domain shifts, detecting fairness issues, and addressing privacy concerns. These motivations can require techniques that reflect underlying model behavior faithfully.","https://schema.org",{"og:url":52,"og:type":87,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":89,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":92},[93,97,101,105,109,114,119,122,127,130,134],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":46,"category_name":107,"show_sort_weight":29,"slug":108},5,"Comic","comic",{"id":110,"doc_module":4,"doc_module_name":46,"category_name":111,"show_sort_weight":112,"slug":113},6,"Technology",50,"technology",{"id":115,"doc_module":4,"doc_module_name":46,"category_name":116,"show_sort_weight":117,"slug":118},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":120,"slug":121},30,"research-report",{"id":123,"doc_module":4,"doc_module_name":46,"category_name":124,"show_sort_weight":125,"slug":126},9,"Religion & Spirituality",20,"religion-spirituality",{"id":125,"doc_module":4,"doc_module_name":46,"category_name":128,"show_sort_weight":125,"slug":129},"World Cup","world-cup",{"id":131,"doc_module":4,"doc_module_name":46,"category_name":132,"show_sort_weight":131,"slug":133},10,"Lifestyle","lifestyle",{"id":135,"doc_module":4,"doc_module_name":46,"category_name":136,"show_sort_weight":106,"slug":137},19,"General","general"]