{"id":11641,"date":"2024-02-06T15:20:08","date_gmt":"2024-02-06T14:20:08","guid":{"rendered":"https:\/\/www.iese.fraunhofer.de\/blog\/?p=11641"},"modified":"2024-02-20T10:32:29","modified_gmt":"2024-02-20T09:32:29","slug":"standardizing-uncertainty-in-machine-learning","status":"publish","type":"post","link":"https:\/\/www.iese.fraunhofer.de\/blog\/standardizing-uncertainty-in-machine-learning\/","title":{"rendered":"DIN SPEC 92005 \u2013 Standardizing uncertainty in machine learning?"},"content":{"rendered":"<p class=\"lead\">DIN SPEC 92005 has been publicly available since January 2024. It deals with the quantification of uncertainties in Machine Learning (ML) and was developed in collaboration with Fraunhofer IESE, which also provided the deputy chairman.<\/p>\n<h4><a href=\"https:\/\/www.iese.fraunhofer.de\/blog\/din-spec-92005-unsicherheit-im-maschinellen-lernen-standardisieren\/\">Dieser Artikel ist auch in Deutsch verf\u00fcgbar: DIN SPEC 92005 \u2013 Unsicherheit im Maschinellen Lernen standardisieren?<\/a><\/h4>\n<h2>DIN SPEC 92005: An important step towards consciously dealing with uncertainty in AI applications<\/h2>\n<div>\n<div class=\"info-box\">\n<p>&#8222;As Deputy Chairman, I am certainly somewhat biased, but I am also firmly convinced that a major step towards better uncertainty management in future AI systems has been taken here under the leadership of DIN. I can therefore recommend to anyone interested in the topic to take a look at <a href=\"https:\/\/www.beuth.de\/de\/technische-regel\/din-spec-92005\/376619718\">DIN SPEC 92005<\/a>, which can be obtained free of charge from Beuth Verlag.&#8220;<\/p>\n<p><em>Dr. Michael Kl\u00e4s, Expert for Safe AI, Fraunhofer IESE<\/em><\/p>\n<\/div>\n<\/div>\n<h2>DIN SPEC 92005 as a solid foundation for practice<\/h2>\n<p>Since ML models are trained on data, residual uncertainty in their output is usually unavoidable. This makes it all the more important, especially for safety-critical AI applications, to reliably determine the uncertainty of their output.<\/p>\n<p><a href=\"https:\/\/dx.doi.org\/10.31030\/3521675\">DIN SPEC 92005<\/a> offers, among other things:<\/p>\n<ul>\n<li>a consolidated <strong>terminology<\/strong>, including an uncertainty ontology (cf. [5])<\/li>\n<li>a practical <strong>classification<\/strong> of sources of uncertainty (cf. [2])<\/li>\n<li>a systematic <strong>overview<\/strong> of different approaches (cf. [1])<\/li>\n<li>a compilation of <strong>requirements<\/strong> for uncertainty quantification<\/li>\n<li>examples on how to <strong>implement<\/strong>\u00a0the requirements with approaches such as uncertainty wrappers<\/li>\n<\/ul>\n<h2>Would you like a broader overview or more details?<\/h2>\n<p>If you need a general overview of quality assurance for ML models, especially in the context of safety-critical AI systems, become a <a href=\"https:\/\/www.iese.fraunhofer.de\/de\/seminare_training\/data-scientist-assuring-safety.html\">Certified Data Scientist Specialized in Assuring Safety<\/a>. Current training dates can be found on the seminar page of the <a href=\"https:\/\/www.bigdata-ai.fraunhofer.de\/de\/data-scientist\/schulungssuche\/certified-data-scientist-specialized-in-assuring-safety.html\">Fraunhofer Big Data and Artificial Intelligence Alliance<\/a> or, with a direct booking option, at <a href=\"https:\/\/www.iese.fraunhofer.de\/de\/seminare_training\/data-scientist-assuring-safety.html\">Fraunhofer IESE<\/a>.<\/p>\n<p>If you are interested in the topic of <a href=\"https:\/\/www.iese.fraunhofer.de\/blog\/uncertainty-management-ki\/\">uncertainty management<\/a> for AI in more detail \u2013 for example, if you are wondering how you can implement the requirements for uncertainty quantification from DIN SPEC 92005 in practice \u2013 you are welcome to contact us. Our <a href=\"https:\/\/www.iese.fraunhofer.de\/blog\/dependable-ai\/\">Dependable AI<\/a> team has been working for years on innovative approaches to reliably determine uncertainty in AI models at runtime and use it to make better decisions.<\/p>\n<h2>Are you interested in the scientific background?<\/h2>\n<p>Here you find a selection of current IESE publications on the topic of uncertainty management for AI models (2018 to 2023):<\/p>\n<ol>\n<li>Kl\u00e4s, M., \u201c<a class=\"\" href=\"https:\/\/arxiv.org\/pdf\/1811.11669\">Towards Identifying and Managing Sources of Uncertainty in AI and Machine Learning Models &#8211; An Overview<\/a>,\u201d arxiv.org\/abs\/1811.11669, 2018.<\/li>\n<li>Kl\u00e4s, M., Vollmer, A. M., \u201c<a class=\"\" href=\"https:\/\/link.springer.com\/chapter\/10.1007\/978-3-319-99229-7_36\">Uncertainty in Machine Learning Applications: A Practice-Driven Classification of Uncertainty<\/a>,\u201d WAISE 2018 at Computer Safety, Reliability, and Security (SAFECOMP 2018), V\u00e4ster\u00e5s, Sweden, 2018.<\/li>\n<li>Kl\u00e4s, M., Sembach, L., \u201c<a class=\"\" href=\"http:\/\/www.klaes.org\/Z-files\/Klaes-2019-WAISE.pdf\">Uncertainty Wrappers for Data-driven Models &#8211; Increase the Transparency of AI\/ML-based Models through Enrichment with Dependable Situation-aware Uncertainty Estimates<\/a>,\u201d WAISE 2019 at Computer Safety, Reliability, and Security (SAFECOMP 2019), Turku, Finland, 2019.<\/li>\n<li>Kl\u00e4s, M., J\u00f6ckel, L., &#8222;<a class=\"\" href=\"https:\/\/link.springer.com\/chapter\/10.1007\/978-3-030-55583-2_23\">A Framework for Building Uncertainty Wrappers for AI\/ML-based Data-Driven Components<\/a>,\u201d WAISE 2020 at Computer Safety, Reliability, and Security (SAFECOMP 2020), Lisbon, Portuga, 2020.<\/li>\n<li>Bandyszak, T., J\u00f6ckel, L., Kl\u00e4s, M., T\u00f6rsleff, S., Weyer, T., Wirtz, B., \u201c<a class=\"\" href=\"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-62136-0_7.pdf\">Handling Uncertainty in Collaborative Embedded Systems Engineering<\/a>,\u201d in: B\u00f6hm W., Broy M., Klein C., Pohl K., Rumpe B., Schr\u00f6ck S. (eds) Model-Based Engineering of Collaborative Embedded Systems. Springer, Cham., 2021. ISBN 978-3-030-62135-3.<\/li>\n<li>Kl\u00e4s, M., Adler, R., Sorokos, I., J\u00f6ckel, L., Reich, J., \u201c<a class=\"\" href=\"https:\/\/www.researchgate.net\/profile\/Ioannis-Sorokos\/publication\/351659571_Handling_Uncertainties_of_Data-Driven_Models_in_Compliance_with_Safety_Constraints_for_Autonomous_Behaviour\/links\/60a39746299bf1d21d6ee26f\/Handling-Uncertainties-of-Data-Driven-Models-in-Compliance-with-Safety-Constraints-for-Autonomous-Behaviour.pdf\">Handling Uncertainties of Data-Driven Models in Compliance with Safety Constraints for Autonomous Behaviour<\/a>,\u201d Proceedings of European Dependable Computing Conference (EDCC 2021), Munich, Germany, 2021.<\/li>\n<li>J\u00f6ckel, L., Kl\u00e4s, M., \u201c<a class=\"\" href=\"https:\/\/link.springer.com\/chapter\/10.1007\/978-3-030-83903-1_2\">Could We Relieve AI\/ML Models of the Responsibility of Providing Dependable Uncertainty Estimates? A Study on Outside-Model Uncertainty Estimates<\/a>,\u201d Proceedings of International Conference on Computer Safety, Reliability and Security (SAFECOMP 2021), York, UK, 2021.<\/li>\n<li>Gro\u00df, J., Adler, R., Kl\u00e4s, M., Reich, J., J\u00f6ckel, L., Gansch, R., &#8222;<a href=\"https:\/\/arxiv.org\/pdf\/2206.06838.pdf\">Architectural patterns for handling runtime uncertainty of data-driven models in safety-critical perception<\/a>,\u201d Proceedings of International Conference on Computer Safety, Reliability and Security (SAFECOMP 2022), Munich, Germany, 2022.<\/li>\n<li>Gerber, P., J\u00f6ckel, L., Kl\u00e4s, M., \u201c<a href=\"https:\/\/ceur-ws.org\/Vol-3087\/paper_7.pdf\">A Study on Mitigating Hard Boundaries of Decision-Tree-based Uncertainty Estimates for AI Models<\/a>,\u201d Proceedings of Artificial Intelligence Safety (SafeAI 2022), 2022.<\/li>\n<li>Gro\u00df, J., Kl\u00e4s, M., J\u00f6ckel, L., Gerber, P., \u201c<a href=\"https:\/\/arxiv.org\/pdf\/2305.14872.pdf\">Timeseries-aware Uncertainty Wrappers for Uncertainty Quantification of Information-Fusion-Enhanced AI Models based on Machine Learning<\/a>,\u201d Proceedings of International Conference on Dependable Systems and Networks Workshops (DSN-W), Porto, Portugal, 2023. 10.1109\/DSN-W58399.2023.00061.<\/li>\n<li>J\u00f6ckel, L., Kl\u00e4s, M., Gro\u00df, J., Gerber, P., \u201c<a href=\"https:\/\/link.springer.com\/chapter\/10.1007\/978-3-031-40953-0_26\">Conformal Prediction and Uncertainty Wrapper: What Statistical Guarantees Can You Get for Uncertainty Quantification in Machine Learning?<\/a>\u201d Proceedings of WAISE 2023 at International Conference on Computer Safety, Reliability and Security (SAFECOMP 2023), York, UK, 2023.<\/li>\n<li>J\u00f6ckel, L., Kl\u00e4s, M., Popp, G., Hilger, N., Fricke, S., \u201c<a href=\"https:\/\/arxiv.org\/pdf\/2311.05245.pdf\">Uncertainty Wrapper in the medical domain: Establishing transparent uncertainty quantification for opaque machine learning models in practice<\/a>,\u201d Submitted to European Dependable Computing Conference (EDCC 2024), Leuven, Belgium, 2024. (arxiv.org\/abs\/2311.05245).<\/li>\n<\/ol>\n","protected":false},"excerpt":{"rendered":"<p>DIN SPEC 92005 has been publicly available since January 2024. It deals with the quantification of uncertainties in Machine Learning (ML) and was developed in collaboration with Fraunhofer IESE, which also provided the deputy chairman. Dieser Artikel ist auch in&#8230;<\/p>\n","protected":false},"author":26,"featured_media":11489,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"_jetpack_memberships_contains_paid_content":false,"footnotes":""},"categories":[177],"tags":[104,415,198,296],"coauthors":[46],"class_list":["post-11641","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-kuenstliche-intelligenz","tag-data-analytics","tag-dependable-ai-verlaessliche-ki","tag-english","tag-machine-learning"],"yoast_head":"<!-- This site is optimized with the Yoast SEO plugin v27.5 - https:\/\/yoast.com\/product\/yoast-seo-wordpress\/ -->\n<title>DIN SPEC 92005 \u2013 Standardizing uncertainty in machine learning? - Blog des Fraunhofer IESE<\/title>\n<meta name=\"description\" content=\"DIN SPEC 92005 has been publicly available since 2024. It deals with the handling of uncertainty in ML and AI applications.\" \/>\n<meta name=\"robots\" content=\"index, follow, max-snippet:-1, max-image-preview:large, max-video-preview:-1\" \/>\n<link rel=\"canonical\" href=\"https:\/\/www.iese.fraunhofer.de\/blog\/standardizing-uncertainty-in-machine-learning\/\" \/>\n<meta property=\"og:locale\" content=\"de_DE\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"DIN SPEC 92005 \u2013 Standardizing uncertainty in machine learning? - Blog des Fraunhofer IESE\" \/>\n<meta property=\"og:description\" content=\"DIN SPEC 92005 has been publicly available since 2024. It deals with the handling of uncertainty in ML and AI applications.\" \/>\n<meta property=\"og:url\" content=\"https:\/\/www.iese.fraunhofer.de\/blog\/standardizing-uncertainty-in-machine-learning\/\" \/>\n<meta property=\"og:site_name\" content=\"Fraunhofer IESE\" \/>\n<meta property=\"article:publisher\" content=\"https:\/\/www.facebook.com\/FraunhoferIESE\/\" \/>\n<meta property=\"article:published_time\" content=\"2024-02-06T14:20:08+00:00\" \/>\n<meta property=\"article:modified_time\" content=\"2024-02-20T09:32:29+00:00\" \/>\n<meta property=\"og:image\" content=\"https:\/\/www.iese.fraunhofer.de\/blog\/wp-content\/uploads\/2024\/01\/DinSpec92005.jpg\" \/>\n\t<meta property=\"og:image:width\" content=\"1409\" \/>\n\t<meta property=\"og:image:height\" content=\"707\" \/>\n\t<meta property=\"og:image:type\" content=\"image\/jpeg\" \/>\n<meta name=\"author\" content=\"Dr. Michael Kl\u00e4s\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:creator\" content=\"@FraunhoferIESE\" \/>\n<meta name=\"twitter:site\" content=\"@FraunhoferIESE\" \/>\n<meta name=\"twitter:label1\" content=\"Verfasst von\" \/>\n\t<meta name=\"twitter:data1\" content=\"Dr. Michael Kl\u00e4s\" \/>\n\t<meta name=\"twitter:label2\" content=\"Gesch\u00e4tzte Lesezeit\" \/>\n\t<meta name=\"twitter:data2\" content=\"4\u00a0Minuten\" \/>\n\t<meta name=\"twitter:label3\" content=\"Written by\" \/>\n\t<meta name=\"twitter:data3\" content=\"Dr. Michael Kl\u00e4s\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\\\/\\\/schema.org\",\"@graph\":[{\"@type\":\"Article\",\"@id\":\"https:\\\/\\\/www.iese.fraunhofer.de\\\/blog\\\/standardizing-uncertainty-in-machine-learning\\\/#article\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/www.iese.fraunhofer.de\\\/blog\\\/standardizing-uncertainty-in-machine-learning\\\/\"},\"author\":{\"name\":\"Dr. Michael Kl\u00e4s\",\"@id\":\"https:\\\/\\\/www.iese.fraunhofer.de\\\/blog\\\/#\\\/schema\\\/person\\\/790f3967298ec81883eb87ed11d86c5e\"},\"headline\":\"DIN SPEC 92005 \u2013 Standardizing uncertainty in machine learning?\",\"datePublished\":\"2024-02-06T14:20:08+00:00\",\"dateModified\":\"2024-02-20T09:32:29+00:00\",\"mainEntityOfPage\":{\"@id\":\"https:\\\/\\\/www.iese.fraunhofer.de\\\/blog\\\/standardizing-uncertainty-in-machine-learning\\\/\"},\"wordCount\":816,\"publisher\":{\"@id\":\"https:\\\/\\\/www.iese.fraunhofer.de\\\/blog\\\/#organization\"},\"image\":{\"@id\":\"https:\\\/\\\/www.iese.fraunhofer.de\\\/blog\\\/standardizing-uncertainty-in-machine-learning\\\/#primaryimage\"},\"thumbnailUrl\":\"https:\\\/\\\/www.iese.fraunhofer.de\\\/blog\\\/wp-content\\\/uploads\\\/2024\\\/01\\\/DinSpec92005.jpg\",\"keywords\":[\"Data Analytics\",\"Dependable AI \\\/ Verl\u00e4ssliche KI\",\"English\",\"Machine Learning\"],\"articleSection\":[\"K\u00fcnstliche Intelligenz\"],\"inLanguage\":\"de\"},{\"@type\":\"WebPage\",\"@id\":\"https:\\\/\\\/www.iese.fraunhofer.de\\\/blog\\\/standardizing-uncertainty-in-machine-learning\\\/\",\"url\":\"https:\\\/\\\/www.iese.fraunhofer.de\\\/blog\\\/standardizing-uncertainty-in-machine-learning\\\/\",\"name\":\"DIN SPEC 92005 \u2013 Standardizing uncertainty in machine learning? - Blog des Fraunhofer IESE\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/www.iese.fraunhofer.de\\\/blog\\\/#website\"},\"primaryImageOfPage\":{\"@id\":\"https:\\\/\\\/www.iese.fraunhofer.de\\\/blog\\\/standardizing-uncertainty-in-machine-learning\\\/#primaryimage\"},\"image\":{\"@id\":\"https:\\\/\\\/www.iese.fraunhofer.de\\\/blog\\\/standardizing-uncertainty-in-machine-learning\\\/#primaryimage\"},\"thumbnailUrl\":\"https:\\\/\\\/www.iese.fraunhofer.de\\\/blog\\\/wp-content\\\/uploads\\\/2024\\\/01\\\/DinSpec92005.jpg\",\"datePublished\":\"2024-02-06T14:20:08+00:00\",\"dateModified\":\"2024-02-20T09:32:29+00:00\",\"description\":\"DIN SPEC 92005 has been publicly available since 2024. It deals with the handling of uncertainty in ML and AI applications.\",\"breadcrumb\":{\"@id\":\"https:\\\/\\\/www.iese.fraunhofer.de\\\/blog\\\/standardizing-uncertainty-in-machine-learning\\\/#breadcrumb\"},\"inLanguage\":\"de\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\\\/\\\/www.iese.fraunhofer.de\\\/blog\\\/standardizing-uncertainty-in-machine-learning\\\/\"]}]},{\"@type\":\"ImageObject\",\"inLanguage\":\"de\",\"@id\":\"https:\\\/\\\/www.iese.fraunhofer.de\\\/blog\\\/standardizing-uncertainty-in-machine-learning\\\/#primaryimage\",\"url\":\"https:\\\/\\\/www.iese.fraunhofer.de\\\/blog\\\/wp-content\\\/uploads\\\/2024\\\/01\\\/DinSpec92005.jpg\",\"contentUrl\":\"https:\\\/\\\/www.iese.fraunhofer.de\\\/blog\\\/wp-content\\\/uploads\\\/2024\\\/01\\\/DinSpec92005.jpg\",\"width\":1409,\"height\":707,\"caption\":\"DIN SPEC 92005 K\u00fcnstliche Intelligenz \u2013 Quantifizierung von Unsicherheiten im Maschinellen Lernen\"},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\\\/\\\/www.iese.fraunhofer.de\\\/blog\\\/standardizing-uncertainty-in-machine-learning\\\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Startseite\",\"item\":\"https:\\\/\\\/www.iese.fraunhofer.de\\\/blog\\\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"DIN SPEC 92005 \u2013 Standardizing uncertainty in machine learning?\"}]},{\"@type\":\"WebSite\",\"@id\":\"https:\\\/\\\/www.iese.fraunhofer.de\\\/blog\\\/#website\",\"url\":\"https:\\\/\\\/www.iese.fraunhofer.de\\\/blog\\\/\",\"name\":\"Fraunhofer IESE\",\"description\":\"Blog des Fraunhofer-Institut f\u00fcr Experimentelles Software Engineering\",\"publisher\":{\"@id\":\"https:\\\/\\\/www.iese.fraunhofer.de\\\/blog\\\/#organization\"},\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\\\/\\\/www.iese.fraunhofer.de\\\/blog\\\/?s={search_term_string}\"},\"query-input\":{\"@type\":\"PropertyValueSpecification\",\"valueRequired\":true,\"valueName\":\"search_term_string\"}}],\"inLanguage\":\"de\"},{\"@type\":\"Organization\",\"@id\":\"https:\\\/\\\/www.iese.fraunhofer.de\\\/blog\\\/#organization\",\"name\":\"Fraunhofer IESE\",\"url\":\"https:\\\/\\\/www.iese.fraunhofer.de\\\/blog\\\/\",\"logo\":{\"@type\":\"ImageObject\",\"inLanguage\":\"de\",\"@id\":\"https:\\\/\\\/www.iese.fraunhofer.de\\\/blog\\\/#\\\/schema\\\/logo\\\/image\\\/\",\"url\":\"https:\\\/\\\/www.iese.fraunhofer.de\\\/blog\\\/wp-content\\\/uploads\\\/2016\\\/08\\\/fhg_iese_logo.png\",\"contentUrl\":\"https:\\\/\\\/www.iese.fraunhofer.de\\\/blog\\\/wp-content\\\/uploads\\\/2016\\\/08\\\/fhg_iese_logo.png\",\"width\":183,\"height\":50,\"caption\":\"Fraunhofer IESE\"},\"image\":{\"@id\":\"https:\\\/\\\/www.iese.fraunhofer.de\\\/blog\\\/#\\\/schema\\\/logo\\\/image\\\/\"},\"sameAs\":[\"https:\\\/\\\/www.facebook.com\\\/FraunhoferIESE\\\/\",\"https:\\\/\\\/x.com\\\/FraunhoferIESE\",\"https:\\\/\\\/www.linkedin.com\\\/company\\\/fraunhoferiese\\\/\",\"https:\\\/\\\/www.youtube.com\\\/c\\\/FraunhoferIESE\"]},{\"@type\":\"Person\",\"@id\":\"https:\\\/\\\/www.iese.fraunhofer.de\\\/blog\\\/#\\\/schema\\\/person\\\/790f3967298ec81883eb87ed11d86c5e\",\"name\":\"Dr. Michael Kl\u00e4s\",\"image\":{\"@type\":\"ImageObject\",\"inLanguage\":\"de\",\"@id\":\"https:\\\/\\\/www.iese.fraunhofer.de\\\/blog\\\/wp-content\\\/uploads\\\/2022\\\/02\\\/klaes_michael-96x96.jpg83e380d8683e0c7345165dedbc8ccb71\",\"url\":\"https:\\\/\\\/www.iese.fraunhofer.de\\\/blog\\\/wp-content\\\/uploads\\\/2022\\\/02\\\/klaes_michael-96x96.jpg\",\"contentUrl\":\"https:\\\/\\\/www.iese.fraunhofer.de\\\/blog\\\/wp-content\\\/uploads\\\/2022\\\/02\\\/klaes_michael-96x96.jpg\",\"caption\":\"Dr. Michael Kl\u00e4s\"},\"description\":\"Dr. Michael Kl\u00e4s ist seit Abschluss seines Informatikstudiums in der angewandten Forschung t\u00e4tig und ber\u00e4t Unternehmen in den Bereichen Softwarequalit\u00e4t und Datenanalyse. Im Laufe der letzten Dekade verantwortete er in zahlreichen Industrie- und Forschungsprojekten insbesondere den Aufbau von KPI-Systemen, die Evaluation neuer Technologien und die Entwicklung pr\u00e4diktiver Analysen. In seiner Dissertation besch\u00e4ftigte er sich mit der Vorhersage von Softwarefehlern unter Einbeziehung von Expertenwissen. Aktuell liegt sein Schwerpunkt im Bereich der Potenzialanalyse f\u00fcr datengetriebene Innovation und der Datenqualit\u00e4ts- und Unsicherheitsanalyse bei Big-Data- und KI-Systemen. Als Autor zahlreicher Fachpublikationen engagiert er sich zudem als Hochschuldozent und als Experte bei der Normierung (DIN\\\/VDE).\",\"url\":\"https:\\\/\\\/www.iese.fraunhofer.de\\\/blog\\\/author\\\/michael-klaes\\\/\"}]}<\/script>\n<!-- \/ Yoast SEO plugin. -->","yoast_head_json":{"title":"DIN SPEC 92005 \u2013 Standardizing uncertainty in machine learning? - Blog des Fraunhofer IESE","description":"DIN SPEC 92005 has been publicly available since 2024. It deals with the handling of uncertainty in ML and AI applications.","robots":{"index":"index","follow":"follow","max-snippet":"max-snippet:-1","max-image-preview":"max-image-preview:large","max-video-preview":"max-video-preview:-1"},"canonical":"https:\/\/www.iese.fraunhofer.de\/blog\/standardizing-uncertainty-in-machine-learning\/","og_locale":"de_DE","og_type":"article","og_title":"DIN SPEC 92005 \u2013 Standardizing uncertainty in machine learning? - Blog des Fraunhofer IESE","og_description":"DIN SPEC 92005 has been publicly available since 2024. It deals with the handling of uncertainty in ML and AI applications.","og_url":"https:\/\/www.iese.fraunhofer.de\/blog\/standardizing-uncertainty-in-machine-learning\/","og_site_name":"Fraunhofer IESE","article_publisher":"https:\/\/www.facebook.com\/FraunhoferIESE\/","article_published_time":"2024-02-06T14:20:08+00:00","article_modified_time":"2024-02-20T09:32:29+00:00","og_image":[{"width":1409,"height":707,"url":"https:\/\/www.iese.fraunhofer.de\/blog\/wp-content\/uploads\/2024\/01\/DinSpec92005.jpg","type":"image\/jpeg"}],"author":"Dr. Michael Kl\u00e4s","twitter_card":"summary_large_image","twitter_creator":"@FraunhoferIESE","twitter_site":"@FraunhoferIESE","twitter_misc":{"Verfasst von":"Dr. Michael Kl\u00e4s","Gesch\u00e4tzte Lesezeit":"4\u00a0Minuten","Written by":"Dr. Michael Kl\u00e4s"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"Article","@id":"https:\/\/www.iese.fraunhofer.de\/blog\/standardizing-uncertainty-in-machine-learning\/#article","isPartOf":{"@id":"https:\/\/www.iese.fraunhofer.de\/blog\/standardizing-uncertainty-in-machine-learning\/"},"author":{"name":"Dr. Michael Kl\u00e4s","@id":"https:\/\/www.iese.fraunhofer.de\/blog\/#\/schema\/person\/790f3967298ec81883eb87ed11d86c5e"},"headline":"DIN SPEC 92005 \u2013 Standardizing uncertainty in machine learning?","datePublished":"2024-02-06T14:20:08+00:00","dateModified":"2024-02-20T09:32:29+00:00","mainEntityOfPage":{"@id":"https:\/\/www.iese.fraunhofer.de\/blog\/standardizing-uncertainty-in-machine-learning\/"},"wordCount":816,"publisher":{"@id":"https:\/\/www.iese.fraunhofer.de\/blog\/#organization"},"image":{"@id":"https:\/\/www.iese.fraunhofer.de\/blog\/standardizing-uncertainty-in-machine-learning\/#primaryimage"},"thumbnailUrl":"https:\/\/www.iese.fraunhofer.de\/blog\/wp-content\/uploads\/2024\/01\/DinSpec92005.jpg","keywords":["Data Analytics","Dependable AI \/ Verl\u00e4ssliche KI","English","Machine Learning"],"articleSection":["K\u00fcnstliche Intelligenz"],"inLanguage":"de"},{"@type":"WebPage","@id":"https:\/\/www.iese.fraunhofer.de\/blog\/standardizing-uncertainty-in-machine-learning\/","url":"https:\/\/www.iese.fraunhofer.de\/blog\/standardizing-uncertainty-in-machine-learning\/","name":"DIN SPEC 92005 \u2013 Standardizing uncertainty in machine learning? - Blog des Fraunhofer IESE","isPartOf":{"@id":"https:\/\/www.iese.fraunhofer.de\/blog\/#website"},"primaryImageOfPage":{"@id":"https:\/\/www.iese.fraunhofer.de\/blog\/standardizing-uncertainty-in-machine-learning\/#primaryimage"},"image":{"@id":"https:\/\/www.iese.fraunhofer.de\/blog\/standardizing-uncertainty-in-machine-learning\/#primaryimage"},"thumbnailUrl":"https:\/\/www.iese.fraunhofer.de\/blog\/wp-content\/uploads\/2024\/01\/DinSpec92005.jpg","datePublished":"2024-02-06T14:20:08+00:00","dateModified":"2024-02-20T09:32:29+00:00","description":"DIN SPEC 92005 has been publicly available since 2024. It deals with the handling of uncertainty in ML and AI applications.","breadcrumb":{"@id":"https:\/\/www.iese.fraunhofer.de\/blog\/standardizing-uncertainty-in-machine-learning\/#breadcrumb"},"inLanguage":"de","potentialAction":[{"@type":"ReadAction","target":["https:\/\/www.iese.fraunhofer.de\/blog\/standardizing-uncertainty-in-machine-learning\/"]}]},{"@type":"ImageObject","inLanguage":"de","@id":"https:\/\/www.iese.fraunhofer.de\/blog\/standardizing-uncertainty-in-machine-learning\/#primaryimage","url":"https:\/\/www.iese.fraunhofer.de\/blog\/wp-content\/uploads\/2024\/01\/DinSpec92005.jpg","contentUrl":"https:\/\/www.iese.fraunhofer.de\/blog\/wp-content\/uploads\/2024\/01\/DinSpec92005.jpg","width":1409,"height":707,"caption":"DIN SPEC 92005 K\u00fcnstliche Intelligenz \u2013 Quantifizierung von Unsicherheiten im Maschinellen Lernen"},{"@type":"BreadcrumbList","@id":"https:\/\/www.iese.fraunhofer.de\/blog\/standardizing-uncertainty-in-machine-learning\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Startseite","item":"https:\/\/www.iese.fraunhofer.de\/blog\/"},{"@type":"ListItem","position":2,"name":"DIN SPEC 92005 \u2013 Standardizing uncertainty in machine learning?"}]},{"@type":"WebSite","@id":"https:\/\/www.iese.fraunhofer.de\/blog\/#website","url":"https:\/\/www.iese.fraunhofer.de\/blog\/","name":"Fraunhofer IESE","description":"Blog des Fraunhofer-Institut f\u00fcr Experimentelles Software Engineering","publisher":{"@id":"https:\/\/www.iese.fraunhofer.de\/blog\/#organization"},"potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/www.iese.fraunhofer.de\/blog\/?s={search_term_string}"},"query-input":{"@type":"PropertyValueSpecification","valueRequired":true,"valueName":"search_term_string"}}],"inLanguage":"de"},{"@type":"Organization","@id":"https:\/\/www.iese.fraunhofer.de\/blog\/#organization","name":"Fraunhofer IESE","url":"https:\/\/www.iese.fraunhofer.de\/blog\/","logo":{"@type":"ImageObject","inLanguage":"de","@id":"https:\/\/www.iese.fraunhofer.de\/blog\/#\/schema\/logo\/image\/","url":"https:\/\/www.iese.fraunhofer.de\/blog\/wp-content\/uploads\/2016\/08\/fhg_iese_logo.png","contentUrl":"https:\/\/www.iese.fraunhofer.de\/blog\/wp-content\/uploads\/2016\/08\/fhg_iese_logo.png","width":183,"height":50,"caption":"Fraunhofer IESE"},"image":{"@id":"https:\/\/www.iese.fraunhofer.de\/blog\/#\/schema\/logo\/image\/"},"sameAs":["https:\/\/www.facebook.com\/FraunhoferIESE\/","https:\/\/x.com\/FraunhoferIESE","https:\/\/www.linkedin.com\/company\/fraunhoferiese\/","https:\/\/www.youtube.com\/c\/FraunhoferIESE"]},{"@type":"Person","@id":"https:\/\/www.iese.fraunhofer.de\/blog\/#\/schema\/person\/790f3967298ec81883eb87ed11d86c5e","name":"Dr. Michael Kl\u00e4s","image":{"@type":"ImageObject","inLanguage":"de","@id":"https:\/\/www.iese.fraunhofer.de\/blog\/wp-content\/uploads\/2022\/02\/klaes_michael-96x96.jpg83e380d8683e0c7345165dedbc8ccb71","url":"https:\/\/www.iese.fraunhofer.de\/blog\/wp-content\/uploads\/2022\/02\/klaes_michael-96x96.jpg","contentUrl":"https:\/\/www.iese.fraunhofer.de\/blog\/wp-content\/uploads\/2022\/02\/klaes_michael-96x96.jpg","caption":"Dr. Michael Kl\u00e4s"},"description":"Dr. Michael Kl\u00e4s ist seit Abschluss seines Informatikstudiums in der angewandten Forschung t\u00e4tig und ber\u00e4t Unternehmen in den Bereichen Softwarequalit\u00e4t und Datenanalyse. Im Laufe der letzten Dekade verantwortete er in zahlreichen Industrie- und Forschungsprojekten insbesondere den Aufbau von KPI-Systemen, die Evaluation neuer Technologien und die Entwicklung pr\u00e4diktiver Analysen. In seiner Dissertation besch\u00e4ftigte er sich mit der Vorhersage von Softwarefehlern unter Einbeziehung von Expertenwissen. Aktuell liegt sein Schwerpunkt im Bereich der Potenzialanalyse f\u00fcr datengetriebene Innovation und der Datenqualit\u00e4ts- und Unsicherheitsanalyse bei Big-Data- und KI-Systemen. Als Autor zahlreicher Fachpublikationen engagiert er sich zudem als Hochschuldozent und als Experte bei der Normierung (DIN\/VDE).","url":"https:\/\/www.iese.fraunhofer.de\/blog\/author\/michael-klaes\/"}]}},"jetpack_featured_media_url":"https:\/\/www.iese.fraunhofer.de\/blog\/wp-content\/uploads\/2024\/01\/DinSpec92005.jpg","jetpack_sharing_enabled":true,"_links":{"self":[{"href":"https:\/\/www.iese.fraunhofer.de\/blog\/wp-json\/wp\/v2\/posts\/11641","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.iese.fraunhofer.de\/blog\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.iese.fraunhofer.de\/blog\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.iese.fraunhofer.de\/blog\/wp-json\/wp\/v2\/users\/26"}],"replies":[{"embeddable":true,"href":"https:\/\/www.iese.fraunhofer.de\/blog\/wp-json\/wp\/v2\/comments?post=11641"}],"version-history":[{"count":5,"href":"https:\/\/www.iese.fraunhofer.de\/blog\/wp-json\/wp\/v2\/posts\/11641\/revisions"}],"predecessor-version":[{"id":11697,"href":"https:\/\/www.iese.fraunhofer.de\/blog\/wp-json\/wp\/v2\/posts\/11641\/revisions\/11697"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.iese.fraunhofer.de\/blog\/wp-json\/wp\/v2\/media\/11489"}],"wp:attachment":[{"href":"https:\/\/www.iese.fraunhofer.de\/blog\/wp-json\/wp\/v2\/media?parent=11641"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.iese.fraunhofer.de\/blog\/wp-json\/wp\/v2\/categories?post=11641"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.iese.fraunhofer.de\/blog\/wp-json\/wp\/v2\/tags?post=11641"},{"taxonomy":"author","embeddable":true,"href":"https:\/\/www.iese.fraunhofer.de\/blog\/wp-json\/wp\/v2\/coauthors?post=11641"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}