{"id":1793,"date":"2020-03-24T18:10:54","date_gmt":"2020-03-24T17:10:54","guid":{"rendered":"https:\/\/www.servicemeister.org\/2020\/03\/24\/vertrauen-in-ki-warum-sich-algorithmen-erklaeren-muessen\/"},"modified":"2020-05-08T09:19:20","modified_gmt":"2020-05-08T07:19:20","slug":"vertrauen-in-ki-warum-sich-algorithmen-erklaeren-muessen","status":"publish","type":"post","link":"https:\/\/www.servicemeister.org\/en\/2020\/03\/24\/vertrauen-in-ki-warum-sich-algorithmen-erklaeren-muessen\/","title":{"rendered":"Trusting in AI: Why algorithms have to explain themselves"},"content":{"rendered":"\n

\u00a9 weerapatkiatdumrong | istockphoto.com <\/p>\n\n\n\n

Cars drive autonomously, software diagnoses cancer and machines control themselves \u2013 artificial intelligence (AI) makes it all possible. But wherever AI supports people, trust in the technology is needed above all. Here is how we can test and certify trusted AI applications.<\/em><\/p>\n\n\n\n

AI helps in the fight\nagainst cancer. From X-rays to CT scans and MRI images \u2013 AI can evaluate them\nand assist physicians in making a diagnosis. To do this, the algorithms analyze\nan enormous amount of data faster than is humanly possible; they mark tumors on\nthe images and present the results to the experts to take a decision on.\nConsequently, physicians can initiate therapies earlier and gain time for their\npatients. However, this improvement in healing prospects also comes with\nproblems since it is not clear which characteristics AI uses to distinguish\ndangerous metastases from harmless cysts.<\/p>\n\n\n\n

Many AI systems are\nnon-transparent. And not only in the health sector. It turns out that the way\nneural networks are modeled on the brain and how they are essential for machine\nlearning is a bit like a black box. Even their creators do not fully understand\nwhat is going on inside them. People can justify and explain their behavior \u2013 neural networks cannot<\/a>. This is a fact that raises\nquestions in areas where smart algorithms already act largely independently,\nbut where decisions must be comprehensible to humans. As a result \u2013 whether it\nbe in the automated granting of micro-loans, personnel selection, or future\ntraffic systems \u2013 people are becoming suspicious and fear losing control, as\ndemonstrated by an Audi study on autonomous driving<\/a> carried out among some 21,000\nconsumers worldwide.<\/p>\n\n\n\n

Evaluate,\nunderstand, and explain<\/strong><\/p>\n\n\n\n

The solution is called\nExplainable Artificial Intelligence: XAI makes AI explicable and makes\nalgorithmic opinion formation comprehensible to humans. But, how can this be\nachieved in practice? One example is to certify AI systems; something the\nFraunhofer Institute for Intelligent Analysis and Information Systems IAIS is working on<\/a>. To this end, the Bonn-based\ncompany has formulated a catalog of requirements for trustworthy AI, which\nenables intelligent applications to be evaluated expertly and neutrally. The\naim here is that certification should guarantee technical reliability and\nresponsible use of the technology. Not only are the AI decisions checked for\ntransparency, they are also checked to see how fairly, securely, and reliably\nalgorithms actually work.<\/a><\/p>\n\n\n\n

Do AI applications protect\nsensitive information? How reliably do the applications work? And are AI\nsystems secure against attacks or errors? \u201cThe problem with many neural\nnetworks is that they cannot be broken down into modules that can be tested\nseparately,\u201d says project leader Dr. Maximilian Poretschkin on heise.de<\/a>. Instead, the experts examine how AI works by\nlooking at the assured properties of an intelligent application. <\/p>\n\n\n\n

Highly dynamic,\nself-learning, and challenging<\/strong><\/p>\n\n\n\n

What makes this project\nchallenging? Test objectives cannot be standardized because there are currently\nno specifications or standards for AI. For example, when vehicles undergo\nsafety inspections, the brakes, engine, and lights are tested as standard,\nhowever these kind of standard inspections do not exist for algorithms.\nFurthermore, AI applications are highly dynamic. Whether self-optimizing,\nself-organizing, or self-learning \u2013 where software works with versions, AI\nsystems develop autonomously and continuously.<\/p>\n\n\n\n

The solution is provided by\na framework developed by the Fraunhofer Institute and presented by Poretschkin\nin a webinar organized by the eco Academy<\/a> (in\nGerman). The\naudit catalog can also be applied in a structured manner to areas of activity\nsuch as fairness, security, privacy, or transparency. The framework looks at\nthe complete life cycle of AI applications. This includes, for example, the\ndesign and architecture of the applications, the training and input data, the\nalgorithm, and the behavior of the AI components themselves. <\/p>\n\n\n\n

Documenting,\nchecking and testing<\/strong><\/p>\n\n\n\n

How might the certification\nbe conducted in practice? AI developers document their work according to the\ncatalog and auditors assess the plausibility of achieving the objectives. The\nstandardized procedure looks at typical risks, defines KPIs, and includes\neverything in the overall assessment. \u201cDepending on the criticality of the AI\napplication, a greater depth of testing is also required, which goes beyond a\npurely documentation-based assessment. We are developing appropriate testing\ntools for this purpose,\u201d says Poretschkin.<\/p>\n\n\n\n

And it\u2019s worth it. After\nall, only those who trust AI will use it. A current AI study by eco \u2013\nAssociation of the Internet Industry<\/a> shows that if the technology is applied across\nall industries and to its full extent, a total economic potential of around 488\nbillion Euros can be released for Germany alone. <\/p>\n\n\n\n

\n\n\n\n

Pease join the discussion on this and similar topics in our Service Meister Linkedin group.<\/strong><\/a><\/p>\n","protected":false},"excerpt":{"rendered":"

Cars drive autonomously, software diagnoses cancer and machines control themselves \u2013 artificial intelligence (AI) makes it all possible. But wherever AI supports people, trust in the technology is needed above all. Here is how we can test and certify trusted AI applications.<\/p>\n","protected":false},"author":5,"featured_media":1771,"comment_status":"closed","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[34],"tags":[],"yoast_head":"\nTrusting in AI: Why algorithms have to explain themselves - Service-Meister<\/title>\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.servicemeister.org\/en\/2020\/03\/24\/vertrauen-in-ki-warum-sich-algorithmen-erklaeren-muessen\/\" \/>\n<meta property=\"og:locale\" content=\"en_US\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"Trusting in AI: Why algorithms have to explain themselves - Service-Meister\" \/>\n<meta property=\"og:description\" content=\"Cars drive autonomously, software diagnoses cancer and machines control themselves \u2013 artificial intelligence (AI) makes it all possible. But wherever AI supports people, trust in the technology is needed above all. Here is how we can test and certify trusted AI applications.\" \/>\n<meta property=\"og:url\" content=\"https:\/\/www.servicemeister.org\/en\/2020\/03\/24\/vertrauen-in-ki-warum-sich-algorithmen-erklaeren-muessen\/\" \/>\n<meta property=\"og:site_name\" content=\"Service-Meister\" \/>\n<meta property=\"article:published_time\" content=\"2020-03-24T17:10:54+00:00\" \/>\n<meta property=\"article:modified_time\" content=\"2020-05-08T07:19:20+00:00\" \/>\n<meta property=\"og:image\" content=\"https:\/\/www.servicemeister.org\/wp-content\/uploads\/2020\/03\/iStock-491959005-copy-992x558-720x405-1.jpg\" \/>\n\t<meta property=\"og:image:width\" content=\"720\" \/>\n\t<meta property=\"og:image:height\" content=\"405\" \/>\n\t<meta property=\"og:image:type\" content=\"image\/jpeg\" \/>\n<meta name=\"author\" content=\"Hauke Timmermann\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:label1\" content=\"Written by\" \/>\n\t<meta name=\"twitter:data1\" content=\"Hauke Timmermann\" \/>\n\t<meta name=\"twitter:label2\" content=\"Est. reading time\" \/>\n\t<meta name=\"twitter:data2\" content=\"4 minutes\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\/\/schema.org\",\"@graph\":[{\"@type\":\"Article\",\"@id\":\"https:\/\/www.servicemeister.org\/en\/2020\/03\/24\/vertrauen-in-ki-warum-sich-algorithmen-erklaeren-muessen\/#article\",\"isPartOf\":{\"@id\":\"https:\/\/www.servicemeister.org\/en\/2020\/03\/24\/vertrauen-in-ki-warum-sich-algorithmen-erklaeren-muessen\/\"},\"author\":{\"name\":\"Hauke Timmermann\",\"@id\":\"https:\/\/www.servicemeister.org\/#\/schema\/person\/1721e0365900aa18e0eacba04dc664fd\"},\"headline\":\"Trusting in AI: Why algorithms have to explain themselves\",\"datePublished\":\"2020-03-24T17:10:54+00:00\",\"dateModified\":\"2020-05-08T07:19:20+00:00\",\"mainEntityOfPage\":{\"@id\":\"https:\/\/www.servicemeister.org\/en\/2020\/03\/24\/vertrauen-in-ki-warum-sich-algorithmen-erklaeren-muessen\/\"},\"wordCount\":771,\"publisher\":{\"@id\":\"https:\/\/www.servicemeister.org\/#organization\"},\"inLanguage\":\"en-US\"},{\"@type\":\"WebPage\",\"@id\":\"https:\/\/www.servicemeister.org\/en\/2020\/03\/24\/vertrauen-in-ki-warum-sich-algorithmen-erklaeren-muessen\/\",\"url\":\"https:\/\/www.servicemeister.org\/en\/2020\/03\/24\/vertrauen-in-ki-warum-sich-algorithmen-erklaeren-muessen\/\",\"name\":\"Trusting in AI: Why algorithms have to explain themselves - Service-Meister\",\"isPartOf\":{\"@id\":\"https:\/\/www.servicemeister.org\/#website\"},\"datePublished\":\"2020-03-24T17:10:54+00:00\",\"dateModified\":\"2020-05-08T07:19:20+00:00\",\"breadcrumb\":{\"@id\":\"https:\/\/www.servicemeister.org\/en\/2020\/03\/24\/vertrauen-in-ki-warum-sich-algorithmen-erklaeren-muessen\/#breadcrumb\"},\"inLanguage\":\"en-US\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\/\/www.servicemeister.org\/en\/2020\/03\/24\/vertrauen-in-ki-warum-sich-algorithmen-erklaeren-muessen\/\"]}]},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\/\/www.servicemeister.org\/en\/2020\/03\/24\/vertrauen-in-ki-warum-sich-algorithmen-erklaeren-muessen\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Startseite\",\"item\":\"https:\/\/www.servicemeister.org\/en\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"Trusting in AI: Why algorithms have to explain themselves\"}]},{\"@type\":\"WebSite\",\"@id\":\"https:\/\/www.servicemeister.org\/#website\",\"url\":\"https:\/\/www.servicemeister.org\/\",\"name\":\"Service-Meister\",\"description\":\"KI Service - Industrie 4.0\",\"publisher\":{\"@id\":\"https:\/\/www.servicemeister.org\/#organization\"},\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\/\/www.servicemeister.org\/?s={search_term_string}\"},\"query-input\":\"required name=search_term_string\"}],\"inLanguage\":\"en-US\"},{\"@type\":\"Organization\",\"@id\":\"https:\/\/www.servicemeister.org\/#organization\",\"name\":\"Service-Meister\",\"url\":\"https:\/\/www.servicemeister.org\/\",\"logo\":{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\/\/www.servicemeister.org\/#\/schema\/logo\/image\/\",\"url\":\"https:\/\/www.servicemeister.org\/wp-content\/uploads\/2019\/05\/cropped-ServiceMeister_Logo.jpg\",\"contentUrl\":\"https:\/\/www.servicemeister.org\/wp-content\/uploads\/2019\/05\/cropped-ServiceMeister_Logo.jpg\",\"width\":1584,\"height\":516,\"caption\":\"Service-Meister\"},\"image\":{\"@id\":\"https:\/\/www.servicemeister.org\/#\/schema\/logo\/image\/\"}},{\"@type\":\"Person\",\"@id\":\"https:\/\/www.servicemeister.org\/#\/schema\/person\/1721e0365900aa18e0eacba04dc664fd\",\"name\":\"Hauke Timmermann\",\"url\":\"https:\/\/www.servicemeister.org\/en\/author\/htn_eco\/\"}]}<\/script>\n<!-- \/ Yoast SEO plugin. -->","yoast_head_json":{"title":"Trusting in AI: Why algorithms have to explain themselves - Service-Meister","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.servicemeister.org\/en\/2020\/03\/24\/vertrauen-in-ki-warum-sich-algorithmen-erklaeren-muessen\/","og_locale":"en_US","og_type":"article","og_title":"Trusting in AI: Why algorithms have to explain themselves - Service-Meister","og_description":"Cars drive autonomously, software diagnoses cancer and machines control themselves \u2013 artificial intelligence (AI) makes it all possible. But wherever AI supports people, trust in the technology is needed above all. Here is how we can test and certify trusted AI applications.","og_url":"https:\/\/www.servicemeister.org\/en\/2020\/03\/24\/vertrauen-in-ki-warum-sich-algorithmen-erklaeren-muessen\/","og_site_name":"Service-Meister","article_published_time":"2020-03-24T17:10:54+00:00","article_modified_time":"2020-05-08T07:19:20+00:00","og_image":[{"width":720,"height":405,"url":"https:\/\/www.servicemeister.org\/wp-content\/uploads\/2020\/03\/iStock-491959005-copy-992x558-720x405-1.jpg","type":"image\/jpeg"}],"author":"Hauke Timmermann","twitter_card":"summary_large_image","twitter_misc":{"Written by":"Hauke Timmermann","Est. reading time":"4 minutes"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"Article","@id":"https:\/\/www.servicemeister.org\/en\/2020\/03\/24\/vertrauen-in-ki-warum-sich-algorithmen-erklaeren-muessen\/#article","isPartOf":{"@id":"https:\/\/www.servicemeister.org\/en\/2020\/03\/24\/vertrauen-in-ki-warum-sich-algorithmen-erklaeren-muessen\/"},"author":{"name":"Hauke Timmermann","@id":"https:\/\/www.servicemeister.org\/#\/schema\/person\/1721e0365900aa18e0eacba04dc664fd"},"headline":"Trusting in AI: Why algorithms have to explain themselves","datePublished":"2020-03-24T17:10:54+00:00","dateModified":"2020-05-08T07:19:20+00:00","mainEntityOfPage":{"@id":"https:\/\/www.servicemeister.org\/en\/2020\/03\/24\/vertrauen-in-ki-warum-sich-algorithmen-erklaeren-muessen\/"},"wordCount":771,"publisher":{"@id":"https:\/\/www.servicemeister.org\/#organization"},"inLanguage":"en-US"},{"@type":"WebPage","@id":"https:\/\/www.servicemeister.org\/en\/2020\/03\/24\/vertrauen-in-ki-warum-sich-algorithmen-erklaeren-muessen\/","url":"https:\/\/www.servicemeister.org\/en\/2020\/03\/24\/vertrauen-in-ki-warum-sich-algorithmen-erklaeren-muessen\/","name":"Trusting in AI: Why algorithms have to explain themselves - Service-Meister","isPartOf":{"@id":"https:\/\/www.servicemeister.org\/#website"},"datePublished":"2020-03-24T17:10:54+00:00","dateModified":"2020-05-08T07:19:20+00:00","breadcrumb":{"@id":"https:\/\/www.servicemeister.org\/en\/2020\/03\/24\/vertrauen-in-ki-warum-sich-algorithmen-erklaeren-muessen\/#breadcrumb"},"inLanguage":"en-US","potentialAction":[{"@type":"ReadAction","target":["https:\/\/www.servicemeister.org\/en\/2020\/03\/24\/vertrauen-in-ki-warum-sich-algorithmen-erklaeren-muessen\/"]}]},{"@type":"BreadcrumbList","@id":"https:\/\/www.servicemeister.org\/en\/2020\/03\/24\/vertrauen-in-ki-warum-sich-algorithmen-erklaeren-muessen\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Startseite","item":"https:\/\/www.servicemeister.org\/en\/"},{"@type":"ListItem","position":2,"name":"Trusting in AI: Why algorithms have to explain themselves"}]},{"@type":"WebSite","@id":"https:\/\/www.servicemeister.org\/#website","url":"https:\/\/www.servicemeister.org\/","name":"Service-Meister","description":"KI Service - Industrie 4.0","publisher":{"@id":"https:\/\/www.servicemeister.org\/#organization"},"potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/www.servicemeister.org\/?s={search_term_string}"},"query-input":"required name=search_term_string"}],"inLanguage":"en-US"},{"@type":"Organization","@id":"https:\/\/www.servicemeister.org\/#organization","name":"Service-Meister","url":"https:\/\/www.servicemeister.org\/","logo":{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/www.servicemeister.org\/#\/schema\/logo\/image\/","url":"https:\/\/www.servicemeister.org\/wp-content\/uploads\/2019\/05\/cropped-ServiceMeister_Logo.jpg","contentUrl":"https:\/\/www.servicemeister.org\/wp-content\/uploads\/2019\/05\/cropped-ServiceMeister_Logo.jpg","width":1584,"height":516,"caption":"Service-Meister"},"image":{"@id":"https:\/\/www.servicemeister.org\/#\/schema\/logo\/image\/"}},{"@type":"Person","@id":"https:\/\/www.servicemeister.org\/#\/schema\/person\/1721e0365900aa18e0eacba04dc664fd","name":"Hauke Timmermann","url":"https:\/\/www.servicemeister.org\/en\/author\/htn_eco\/"}]}},"_links":{"self":[{"href":"https:\/\/www.servicemeister.org\/en\/wp-json\/wp\/v2\/posts\/1793"}],"collection":[{"href":"https:\/\/www.servicemeister.org\/en\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.servicemeister.org\/en\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.servicemeister.org\/en\/wp-json\/wp\/v2\/users\/5"}],"replies":[{"embeddable":true,"href":"https:\/\/www.servicemeister.org\/en\/wp-json\/wp\/v2\/comments?post=1793"}],"version-history":[{"count":2,"href":"https:\/\/www.servicemeister.org\/en\/wp-json\/wp\/v2\/posts\/1793\/revisions"}],"predecessor-version":[{"id":1835,"href":"https:\/\/www.servicemeister.org\/en\/wp-json\/wp\/v2\/posts\/1793\/revisions\/1835"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.servicemeister.org\/en\/wp-json\/wp\/v2\/media\/1771"}],"wp:attachment":[{"href":"https:\/\/www.servicemeister.org\/en\/wp-json\/wp\/v2\/media?parent=1793"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.servicemeister.org\/en\/wp-json\/wp\/v2\/categories?post=1793"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.servicemeister.org\/en\/wp-json\/wp\/v2\/tags?post=1793"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}