{"id":216929,"date":"2025-07-01T06:17:15","date_gmt":"2025-07-01T11:17:15","guid":{"rendered":"https:\/\/lifeboat.com\/blog\/2025\/07\/mathematical-approach-makes-uncertainty-in-ai-quantifiable"},"modified":"2025-07-01T06:17:15","modified_gmt":"2025-07-01T11:17:15","slug":"mathematical-approach-makes-uncertainty-in-ai-quantifiable","status":"publish","type":"post","link":"https:\/\/lifeboat.com\/blog\/2025\/07\/mathematical-approach-makes-uncertainty-in-ai-quantifiable","title":{"rendered":"Mathematical approach makes uncertainty in AI quantifiable"},"content":{"rendered":"<p><a class=\"aligncenter blog-photo\" href=\"https:\/\/lifeboat.com\/blog.images\/mathematical-approach-makes-uncertainty-in-ai-quantifiable2.jpg\"><\/a><\/p>\n<p>How reliable is artificial intelligence, really? An interdisciplinary research team at TU Wien has developed a method that allows for the exact calculation of how reliably a neural network operates within a defined input domain. In other words: It is now possible to mathematically guarantee that certain types of errors will not occur\u2014a crucial step forward for the safe use of AI in sensitive applications.<\/p>\n<p>From smartphones to self-driving cars, AI systems have become an everyday part of our lives. But in applications where safety is critical, one central question arises: Can we guarantee that an AI system won\u2019t make serious mistakes\u2014even when its input varies slightly?<\/p>\n<p>A team from TU Wien\u2014Dr. Andrey Kofnov, Dr. Daniel Kapla, Prof. Efstathia Bura and Prof. Ezio Bartocci\u2014bringing together experts from mathematics, statistics and computer science, has now found a way to analyze neural networks, the brains of AI systems, in such a way that the possible range of outputs can be exactly determined for a given input range\u2014and specific errors can be ruled out with certainty.<\/p>\n","protected":false},"excerpt":{"rendered":"<p>How reliable is artificial intelligence, really? An interdisciplinary research team at TU Wien has developed a method that allows for the exact calculation of how reliably a neural network operates within a defined input domain. In other words: It is now possible to mathematically guarantee that certain types of errors will not occur\u2014a crucial step [\u2026]<\/p>\n","protected":false},"author":427,"featured_media":0,"comment_status":"open","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[2229,1512,6,1491],"tags":[],"class_list":["post-216929","post","type-post","status-publish","format-standard","hentry","category-mathematics","category-mobile-phones","category-robotics-ai","category-transportation"],"_links":{"self":[{"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/posts\/216929","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/users\/427"}],"replies":[{"embeddable":true,"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/comments?post=216929"}],"version-history":[{"count":0,"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/posts\/216929\/revisions"}],"wp:attachment":[{"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/media?parent=216929"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/categories?post=216929"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/tags?post=216929"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}