{"id":1508,"date":"2020-12-01T10:37:13","date_gmt":"2020-12-01T10:37:13","guid":{"rendered":"http:\/\/horizon.peachpuff-wolverine-566518.hostingersite.com\/?p=1508"},"modified":"2020-12-01T10:37:13","modified_gmt":"2020-12-01T10:37:13","slug":"opening-the-black-box-of-artificial-intelligence","status":"publish","type":"post","link":"https:\/\/scienceblog.com\/horizon\/1508\/opening-the-black-box-of-artificial-intelligence\/","title":{"rendered":"Opening the \u2018black box\u2019 of artificial intelligence"},"content":{"rendered":"
\n
\n
\n

Artificial intelligence is growing ever more powerful and entering people\u2019s daily lives, yet often we don\u2019t know what goes on inside these systems. Their non-transparency could fuel practical problems, or even racism, which is why researchers increasingly want to open this \u2018black box\u2019 and make AI explainable.<\/strong><\/p>\n<\/div>\n<\/div>\n<\/div>\n

\n
\n
\n

In February of 2013, Eric Loomis was driving around in the small town of La Crosse in Wisconsin, US, when he was stopped by the police. The car he was driving turned out to have been involved in a shooting, and he was arrested. Eventually a court\u00a0sentenced<\/a> him to six years in prison.<\/p>\n

This might have been an uneventful case, had it not been for a piece of technology that had aided the judge in making the decision. They used COMPAS, an algorithm that determines the risk of a defendant becoming a recidivist. The court inputs a range of data, like the defendant\u2019s demographic information, into the system, which yields a score of how likely they are to again commit a crime.<\/p>\n

How the algorithm predicts this, however, remains non-transparent. The system, in other words, is a black box \u2013 a practice against which Loomis made a 2017 complaint in the US Supreme Court. He claimed COMPAS used gender and racial data to make its decisions, and ranked Afro-Americans as higher recidivism risks. The court eventually\u00a0rejected<\/a>\u00a0his case, claiming the sentence would have been the same even without the algorithm. Yet there have also been a number of\u00a0revelations<\/a>\u00a0which suggest COMPAS doesn\u2019t accurately predict recidivism.<\/p>\n

Adoption<\/strong><\/p>\n

While algorithmic sentencing systems are already in use in the US, in Europe their adoption has generally been limited. A\u00a0Dutch AI sentencing system<\/a>, that judged on private cases like late payments to companies, was for example shut down in 2018 after critical media coverage. Yet AI has entered into other fields across Europe. It is being rolled out to help European doctors diagnose\u00a0Covid-19<\/a>. And start-ups like the British\u00a0M:QUBE<\/a>, which uses AI to analyse mortgage applications, are popping up fast.<\/p>\n

These systems run historical data through an algorithm, which then comes up with a prediction or course of action. Yet often we don\u2019t know how such a system reaches its conclusion. It might work correctly, or it might have a technical error inside of it. It might even reproduce some form of bias, like racism, without the designers even realising it.<\/p>\n

This is why researchers want to open this black box, and make AI systems transparent, or \u2018explainable\u2019, a movement that is now picking up steam. The\u00a0EU White Paper on Artificial Intelligence<\/a>\u00a0released earlier this year called for explainable AI, major companies like\u00a0Google<\/a>\u00a0and\u00a0IBM<\/a>\u00a0are funding research into it and GDPR even includes a right to explainability for consumers.<\/p>\n

\u2018We are now able to produce AI models that are very efficient in making decisions,\u2019 said Fosca Giannotti, senior researcher at the Information Science and Technology Institute of the National Research Council in Pisa, Italy. \u2018But often these models are impossible to understand for the end-user, which is why explainable AI is becoming so popular.\u2019<\/p>\n

Diagnosis<\/strong><\/p>\n

Giannotti leads a research project on explainable AI, called\u00a0XAI<\/a>, which wants to make AI systems reveal their internal logic. The project works on automated decision support systems like technology that helps a doctor make a diagnosis or algorithms that recommend to banks whether or not to give someone a loan. They hope to develop the technical methods or even new algorithms that can help make AI explainable.<\/p>\n

\u2018Humans still make the final decisions in these systems,’ said Giannotti. \u2018But every human that uses these systems should have a clear understanding of the logic behind the suggestion. \u2019<\/p>\n

Today, hospitals and doctors increasingly experiment with\u00a0AI systems<\/a>\u00a0to support their decisions, but are often unaware of how the decision was made. AI in this case analyses large amounts of medical data, and yields a percentage of likelihood a patient has a certain disease.<\/p>\n

For example, a system might be trained on large amounts of photos of human skin, which in some cases represent symptoms of skin cancer. Based on that data, it predicts whether someone is likely to have skin cancer from new pictures of a skin anomaly. These systems are not general practice yet, but hospitals are increasingly testing them, and integrating them in their daily work.<\/p>\n

These systems often use a popular AI method called deep learning, that takes large amounts of small sub-decisions. These are grouped into a network with layers that can range from a few dozen up to hundreds deep, making it particularly hard to see why the system suggested someone has skin cancer, for example, or to identify faulty reasoning.<\/p>\n

\u2018Sometimes even the computer scientist who designed the network cannot really understand the logic,’ said Giannotti.<\/p>\n

Natural language<\/strong><\/p>\n

For Sen\u00e9n Barro, professor of computer science and artificial intelligence at the University of Santiago de Compostela in Spain, AI should not only be able to justify its decisions but do so using human language.<\/p>\n

\u2018Explainable AI should be able to communicate the outcome naturally to humans, but also the reasoning process that justifies the result,\u2019 said Prof. Barro.<\/p>\n

He is scientific coordinator of a project called\u00a0NL4XAI<\/a>\u00a0which is training researchers on how to make AI systems explainable, by exploring different sub-areas such as specific techniques to accomplish explainability.<\/p>\n

He says that the end result could look similar to a chatbot. \u2018Natural language technology can build conversational agents that convey these interactive explanations to humans,\u2019 he said.<\/p>\n

\n
\n

\u2018Explainable AI should be able to communicate the outcome naturally to humans, but also the reasoning process that justifies the result.\u2019<\/p>\n

Prof. Sen\u00e9n Barro, University of Santiago de Compostela Spain<\/p>\n<\/blockquote>\n<\/div>\n

Another method to give explanations is for the system to provide a counterfactual. \u2018It might mean that the system gives an example of what someone would need to change to alter the solution,\u2019 said Giannotti. In the case of a loan-judging algorithm, a counterfactual might show to someone whose loan was denied what the nearest case would be where they would be approved. It might say that someone\u2019s salary is too low, but if they earned \u20ac1,000 more on a yearly basis, they would be eligible.<\/p>\n

White box<\/strong><\/p>\n

Giannotti says there are two main approaches to explainability. One is to start from black box algorithms, which are not capable of explaining their results themselves, and find ways to uncover their inner logic. Researchers can attach another algorithm to this black box system \u2013 an \u2018explanator\u2019 \u2013 which asks a range of questions of the black box and compares the results with the input it offered. From this process the explanator can reconstruct how the black box system works.<\/p>\n

\u2018But another way is just to throw away the black box, and use white box algorithms, \u2019 said Giannotti. These are machine learning systems that are explainable by design, yet often are less powerful than their black box counterparts.<\/p>\n

\u2018We cannot yet say which approach is better,\u2019 cautioned Giannotti. \u2018The choice depends on the data we are working on.\u2019 When analysing very big amounts of data, like a database filled with high-resolution images, a black box system is often needed because they are more powerful. But for lighter tasks, a white box algorithm might work better.<\/p>\n

Finding the right approach to achieving explainability is still a big problem though. Researchers need to find technical measures to see whether an explanation actually explains a black-box system well. \u2018The biggest challenge is on defining new evaluation protocols to validate the goodness and effectiveness of the generated explanation,\u2019 said Prof. Barro of NL4XAI.<\/p>\n

On top of that, the exact definition of explainability is somewhat unclear, and depends on the situation in which it is applied. An AI researcher who writes an algorithm will need a different kind of explanation compared to a doctor who uses a system to make medical diagnoses.<\/p>\n

\u2018Human evaluation (of the system\u2019s output) is inherently subjective since it depends on the background of the person who interacts with the intelligent machine,\u2019 said Dr Jose Mar\u00eda Alonso, deputy coordinator of NL4XAI and also a researcher at the University of Santiago de Compostela.<\/p>\n

Yet the drive for explainable AI is moving along step by step, which would improve cooperation between humans and machines. \u2018Humans won’t be replaced by AI,’ said Giannotti. \u2018They will be amplified by computers. But explanation is an important precondition for this cooperation.\u2019<\/p>\n

The research in this article was funded by the EU. If you liked this article, please consider sharing it on social media.<\/em><\/p>\n

Published by Horizon<\/a>\u00a0<\/em><\/p>\n<\/div>\n<\/div>\n<\/div>\n","protected":false},"excerpt":{"rendered":"

Artificial intelligence is growing ever more powerful and entering people\u2019s daily lives, yet often we don\u2019t know what goes on inside these systems. Their non-transparency could fuel practical problems, or even racism, which is why researchers increasingly want to open this \u2018black box\u2019 and make AI explainable. In February of 2013, Eric Loomis was driving … Read more<\/a><\/p>\n","protected":false},"author":298,"featured_media":1509,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"generate_page_header":"","jetpack_post_was_ever_published":false,"_jetpack_newsletter_access":"","_jetpack_dont_email_post_to_subs":false,"_jetpack_newsletter_tier_id":0,"_jetpack_memberships_contains_paywalled_content":false,"_jetpack_memberships_contains_paid_content":false,"footnotes":""},"categories":[112],"tags":[],"class_list":["post-1508","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-ict"],"yoast_head":"\nOpening the \u2018black box\u2019 of artificial intelligence - Horizon Magazine Blog<\/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:\/\/scienceblog.com\/horizon\/1508\/opening-the-black-box-of-artificial-intelligence\/\" \/>\n<meta property=\"og:locale\" content=\"en_US\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"Opening the \u2018black box\u2019 of artificial intelligence\" \/>\n<meta property=\"og:description\" content=\"Artificial intelligence is growing ever more powerful and entering people\u2019s daily lives, yet often we don\u2019t know what goes on inside these systems. Their non-transparency could fuel practical problems, or even racism, which is why researchers increasingly want to open this \u2018black box\u2019 and make AI explainable. In February of 2013, Eric Loomis was driving ... Read more\" \/>\n<meta property=\"og:url\" content=\"https:\/\/scienceblog.com\/horizon\/1508\/opening-the-black-box-of-artificial-intelligence\/\" \/>\n<meta property=\"og:site_name\" content=\"Horizon Magazine Blog\" \/>\n<meta property=\"article:author\" content=\"https:\/\/www.facebook.com\/horizon.magazine.eu\" \/>\n<meta property=\"article:published_time\" content=\"2020-12-01T10:37:13+00:00\" \/>\n<meta property=\"og:image\" content=\"https:\/\/scienceblog.com\/horizon\/wp-content\/uploads\/sites\/4\/2020\/12\/algorithm.jpg\" \/>\n\t<meta property=\"og:image:width\" content=\"1024\" \/>\n\t<meta property=\"og:image:height\" content=\"722\" \/>\n\t<meta property=\"og:image:type\" content=\"image\/jpeg\" \/>\n<meta name=\"author\" content=\"Horizon Magazine\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:creator\" content=\"@https:\/\/twitter.com\/HorizonMagEU\" \/>\n<meta name=\"twitter:label1\" content=\"Written by\" \/>\n\t<meta name=\"twitter:data1\" content=\"Horizon Magazine\" \/>\n\t<meta name=\"twitter:label2\" content=\"Est. reading time\" \/>\n\t<meta name=\"twitter:data2\" content=\"7 minutes\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\\\/\\\/schema.org\",\"@graph\":[{\"@type\":\"Article\",\"@id\":\"https:\\\/\\\/scienceblog.com\\\/horizon\\\/1508\\\/opening-the-black-box-of-artificial-intelligence\\\/#article\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/scienceblog.com\\\/horizon\\\/1508\\\/opening-the-black-box-of-artificial-intelligence\\\/\"},\"author\":{\"name\":\"Horizon Magazine\",\"@id\":\"https:\\\/\\\/scienceblog.com\\\/horizon\\\/#\\\/schema\\\/person\\\/8f23522ba58f477f04dd574e1034f679\"},\"headline\":\"Opening the \u2018black box\u2019 of artificial intelligence\",\"datePublished\":\"2020-12-01T10:37:13+00:00\",\"mainEntityOfPage\":{\"@id\":\"https:\\\/\\\/scienceblog.com\\\/horizon\\\/1508\\\/opening-the-black-box-of-artificial-intelligence\\\/\"},\"wordCount\":1439,\"publisher\":{\"@id\":\"https:\\\/\\\/scienceblog.com\\\/horizon\\\/#organization\"},\"image\":{\"@id\":\"https:\\\/\\\/scienceblog.com\\\/horizon\\\/1508\\\/opening-the-black-box-of-artificial-intelligence\\\/#primaryimage\"},\"thumbnailUrl\":\"https:\\\/\\\/scienceblog.com\\\/horizon\\\/wp-content\\\/uploads\\\/sites\\\/4\\\/2020\\\/12\\\/algorithm.jpg\",\"articleSection\":[\"ICT\"],\"inLanguage\":\"en-US\",\"copyrightYear\":\"2020\",\"copyrightHolder\":{\"@id\":\"https:\\\/\\\/scienceblog.com\\\/#organization\"}},{\"@type\":\"WebPage\",\"@id\":\"https:\\\/\\\/scienceblog.com\\\/horizon\\\/1508\\\/opening-the-black-box-of-artificial-intelligence\\\/\",\"url\":\"https:\\\/\\\/scienceblog.com\\\/horizon\\\/1508\\\/opening-the-black-box-of-artificial-intelligence\\\/\",\"name\":\"Opening the \u2018black box\u2019 of artificial intelligence - Horizon Magazine Blog\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/scienceblog.com\\\/horizon\\\/#website\"},\"primaryImageOfPage\":{\"@id\":\"https:\\\/\\\/scienceblog.com\\\/horizon\\\/1508\\\/opening-the-black-box-of-artificial-intelligence\\\/#primaryimage\"},\"image\":{\"@id\":\"https:\\\/\\\/scienceblog.com\\\/horizon\\\/1508\\\/opening-the-black-box-of-artificial-intelligence\\\/#primaryimage\"},\"thumbnailUrl\":\"https:\\\/\\\/scienceblog.com\\\/horizon\\\/wp-content\\\/uploads\\\/sites\\\/4\\\/2020\\\/12\\\/algorithm.jpg\",\"datePublished\":\"2020-12-01T10:37:13+00:00\",\"breadcrumb\":{\"@id\":\"https:\\\/\\\/scienceblog.com\\\/horizon\\\/1508\\\/opening-the-black-box-of-artificial-intelligence\\\/#breadcrumb\"},\"inLanguage\":\"en-US\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\\\/\\\/scienceblog.com\\\/horizon\\\/1508\\\/opening-the-black-box-of-artificial-intelligence\\\/\"]}]},{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\\\/\\\/scienceblog.com\\\/horizon\\\/1508\\\/opening-the-black-box-of-artificial-intelligence\\\/#primaryimage\",\"url\":\"https:\\\/\\\/scienceblog.com\\\/horizon\\\/wp-content\\\/uploads\\\/sites\\\/4\\\/2020\\\/12\\\/algorithm.jpg\",\"contentUrl\":\"https:\\\/\\\/scienceblog.com\\\/horizon\\\/wp-content\\\/uploads\\\/sites\\\/4\\\/2020\\\/12\\\/algorithm.jpg\",\"width\":1024,\"height\":722,\"caption\":\"When decisions are made by artificial intelligence, it can be difficult for the end user to understand the reasoning behind them.\"},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\\\/\\\/scienceblog.com\\\/horizon\\\/1508\\\/opening-the-black-box-of-artificial-intelligence\\\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Home\",\"item\":\"https:\\\/\\\/scienceblog.com\\\/horizon\\\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"Opening the \u2018black box\u2019 of artificial intelligence\"}]},{\"@type\":\"WebSite\",\"@id\":\"https:\\\/\\\/scienceblog.com\\\/horizon\\\/#website\",\"url\":\"https:\\\/\\\/scienceblog.com\\\/horizon\\\/\",\"name\":\"Horizon Magazine Blog\",\"description\":\"The EU Research & Innovation Magazine\",\"publisher\":{\"@id\":\"https:\\\/\\\/scienceblog.com\\\/horizon\\\/#organization\"},\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\\\/\\\/scienceblog.com\\\/horizon\\\/?s={search_term_string}\"},\"query-input\":{\"@type\":\"PropertyValueSpecification\",\"valueRequired\":true,\"valueName\":\"search_term_string\"}}],\"inLanguage\":\"en-US\"},{\"@type\":\"Organization\",\"@id\":\"https:\\\/\\\/scienceblog.com\\\/horizon\\\/#organization\",\"name\":\"Horizon Magazine Blog\",\"url\":\"https:\\\/\\\/scienceblog.com\\\/horizon\\\/\",\"logo\":{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\\\/\\\/scienceblog.com\\\/horizon\\\/#\\\/schema\\\/logo\\\/image\\\/\",\"url\":\"https:\\\/\\\/scienceblog.com\\\/horizon\\\/wp-content\\\/uploads\\\/sites\\\/4\\\/2026\\\/04\\\/eu-logo.jpg\",\"contentUrl\":\"https:\\\/\\\/scienceblog.com\\\/horizon\\\/wp-content\\\/uploads\\\/sites\\\/4\\\/2026\\\/04\\\/eu-logo.jpg\",\"width\":601,\"height\":283,\"caption\":\"Horizon Magazine Blog\"},\"image\":{\"@id\":\"https:\\\/\\\/scienceblog.com\\\/horizon\\\/#\\\/schema\\\/logo\\\/image\\\/\"}},{\"@type\":\"Person\",\"@id\":\"https:\\\/\\\/scienceblog.com\\\/horizon\\\/#\\\/schema\\\/person\\\/8f23522ba58f477f04dd574e1034f679\",\"name\":\"Horizon Magazine\",\"image\":{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\\\/\\\/secure.gravatar.com\\\/avatar\\\/407bd816be829798850d5e7f646c4137f70c86c6af6c761b67a6ea80c364ffa4?s=96&d=mm&r=g\",\"url\":\"https:\\\/\\\/secure.gravatar.com\\\/avatar\\\/407bd816be829798850d5e7f646c4137f70c86c6af6c761b67a6ea80c364ffa4?s=96&d=mm&r=g\",\"contentUrl\":\"https:\\\/\\\/secure.gravatar.com\\\/avatar\\\/407bd816be829798850d5e7f646c4137f70c86c6af6c761b67a6ea80c364ffa4?s=96&d=mm&r=g\",\"caption\":\"Horizon Magazine\"},\"sameAs\":[\"https:\\\/\\\/www.facebook.com\\\/horizon.magazine.eu\",\"https:\\\/\\\/x.com\\\/https:\\\/\\\/twitter.com\\\/HorizonMagEU\"],\"url\":\"https:\\\/\\\/scienceblog.com\\\/horizon\\\/author\\\/horizonmagazine\\\/\"}]}<\/script>\n<!-- \/ Yoast SEO Premium plugin. -->","yoast_head_json":{"title":"Opening the \u2018black box\u2019 of artificial intelligence - Horizon Magazine Blog","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:\/\/scienceblog.com\/horizon\/1508\/opening-the-black-box-of-artificial-intelligence\/","og_locale":"en_US","og_type":"article","og_title":"Opening the \u2018black box\u2019 of artificial intelligence","og_description":"Artificial intelligence is growing ever more powerful and entering people\u2019s daily lives, yet often we don\u2019t know what goes on inside these systems. Their non-transparency could fuel practical problems, or even racism, which is why researchers increasingly want to open this \u2018black box\u2019 and make AI explainable. In February of 2013, Eric Loomis was driving ... Read more","og_url":"https:\/\/scienceblog.com\/horizon\/1508\/opening-the-black-box-of-artificial-intelligence\/","og_site_name":"Horizon Magazine Blog","article_author":"https:\/\/www.facebook.com\/horizon.magazine.eu","article_published_time":"2020-12-01T10:37:13+00:00","og_image":[{"width":1024,"height":722,"url":"https:\/\/scienceblog.com\/horizon\/wp-content\/uploads\/sites\/4\/2020\/12\/algorithm.jpg","type":"image\/jpeg"}],"author":"Horizon Magazine","twitter_card":"summary_large_image","twitter_creator":"@https:\/\/twitter.com\/HorizonMagEU","twitter_misc":{"Written by":"Horizon Magazine","Est. reading time":"7 minutes"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"Article","@id":"https:\/\/scienceblog.com\/horizon\/1508\/opening-the-black-box-of-artificial-intelligence\/#article","isPartOf":{"@id":"https:\/\/scienceblog.com\/horizon\/1508\/opening-the-black-box-of-artificial-intelligence\/"},"author":{"name":"Horizon Magazine","@id":"https:\/\/scienceblog.com\/horizon\/#\/schema\/person\/8f23522ba58f477f04dd574e1034f679"},"headline":"Opening the \u2018black box\u2019 of artificial intelligence","datePublished":"2020-12-01T10:37:13+00:00","mainEntityOfPage":{"@id":"https:\/\/scienceblog.com\/horizon\/1508\/opening-the-black-box-of-artificial-intelligence\/"},"wordCount":1439,"publisher":{"@id":"https:\/\/scienceblog.com\/horizon\/#organization"},"image":{"@id":"https:\/\/scienceblog.com\/horizon\/1508\/opening-the-black-box-of-artificial-intelligence\/#primaryimage"},"thumbnailUrl":"https:\/\/scienceblog.com\/horizon\/wp-content\/uploads\/sites\/4\/2020\/12\/algorithm.jpg","articleSection":["ICT"],"inLanguage":"en-US","copyrightYear":"2020","copyrightHolder":{"@id":"https:\/\/scienceblog.com\/#organization"}},{"@type":"WebPage","@id":"https:\/\/scienceblog.com\/horizon\/1508\/opening-the-black-box-of-artificial-intelligence\/","url":"https:\/\/scienceblog.com\/horizon\/1508\/opening-the-black-box-of-artificial-intelligence\/","name":"Opening the \u2018black box\u2019 of artificial intelligence - Horizon Magazine Blog","isPartOf":{"@id":"https:\/\/scienceblog.com\/horizon\/#website"},"primaryImageOfPage":{"@id":"https:\/\/scienceblog.com\/horizon\/1508\/opening-the-black-box-of-artificial-intelligence\/#primaryimage"},"image":{"@id":"https:\/\/scienceblog.com\/horizon\/1508\/opening-the-black-box-of-artificial-intelligence\/#primaryimage"},"thumbnailUrl":"https:\/\/scienceblog.com\/horizon\/wp-content\/uploads\/sites\/4\/2020\/12\/algorithm.jpg","datePublished":"2020-12-01T10:37:13+00:00","breadcrumb":{"@id":"https:\/\/scienceblog.com\/horizon\/1508\/opening-the-black-box-of-artificial-intelligence\/#breadcrumb"},"inLanguage":"en-US","potentialAction":[{"@type":"ReadAction","target":["https:\/\/scienceblog.com\/horizon\/1508\/opening-the-black-box-of-artificial-intelligence\/"]}]},{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/scienceblog.com\/horizon\/1508\/opening-the-black-box-of-artificial-intelligence\/#primaryimage","url":"https:\/\/scienceblog.com\/horizon\/wp-content\/uploads\/sites\/4\/2020\/12\/algorithm.jpg","contentUrl":"https:\/\/scienceblog.com\/horizon\/wp-content\/uploads\/sites\/4\/2020\/12\/algorithm.jpg","width":1024,"height":722,"caption":"When decisions are made by artificial intelligence, it can be difficult for the end user to understand the reasoning behind them."},{"@type":"BreadcrumbList","@id":"https:\/\/scienceblog.com\/horizon\/1508\/opening-the-black-box-of-artificial-intelligence\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https:\/\/scienceblog.com\/horizon\/"},{"@type":"ListItem","position":2,"name":"Opening the \u2018black box\u2019 of artificial intelligence"}]},{"@type":"WebSite","@id":"https:\/\/scienceblog.com\/horizon\/#website","url":"https:\/\/scienceblog.com\/horizon\/","name":"Horizon Magazine Blog","description":"The EU Research & Innovation Magazine","publisher":{"@id":"https:\/\/scienceblog.com\/horizon\/#organization"},"potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/scienceblog.com\/horizon\/?s={search_term_string}"},"query-input":{"@type":"PropertyValueSpecification","valueRequired":true,"valueName":"search_term_string"}}],"inLanguage":"en-US"},{"@type":"Organization","@id":"https:\/\/scienceblog.com\/horizon\/#organization","name":"Horizon Magazine Blog","url":"https:\/\/scienceblog.com\/horizon\/","logo":{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/scienceblog.com\/horizon\/#\/schema\/logo\/image\/","url":"https:\/\/scienceblog.com\/horizon\/wp-content\/uploads\/sites\/4\/2026\/04\/eu-logo.jpg","contentUrl":"https:\/\/scienceblog.com\/horizon\/wp-content\/uploads\/sites\/4\/2026\/04\/eu-logo.jpg","width":601,"height":283,"caption":"Horizon Magazine Blog"},"image":{"@id":"https:\/\/scienceblog.com\/horizon\/#\/schema\/logo\/image\/"}},{"@type":"Person","@id":"https:\/\/scienceblog.com\/horizon\/#\/schema\/person\/8f23522ba58f477f04dd574e1034f679","name":"Horizon Magazine","image":{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/secure.gravatar.com\/avatar\/407bd816be829798850d5e7f646c4137f70c86c6af6c761b67a6ea80c364ffa4?s=96&d=mm&r=g","url":"https:\/\/secure.gravatar.com\/avatar\/407bd816be829798850d5e7f646c4137f70c86c6af6c761b67a6ea80c364ffa4?s=96&d=mm&r=g","contentUrl":"https:\/\/secure.gravatar.com\/avatar\/407bd816be829798850d5e7f646c4137f70c86c6af6c761b67a6ea80c364ffa4?s=96&d=mm&r=g","caption":"Horizon Magazine"},"sameAs":["https:\/\/www.facebook.com\/horizon.magazine.eu","https:\/\/x.com\/https:\/\/twitter.com\/HorizonMagEU"],"url":"https:\/\/scienceblog.com\/horizon\/author\/horizonmagazine\/"}]}},"jetpack_featured_media_url":"https:\/\/scienceblog.com\/horizon\/wp-content\/uploads\/sites\/4\/2020\/12\/algorithm.jpg","jetpack_shortlink":"https:\/\/wp.me\/pgtNKV-ok","jetpack_sharing_enabled":true,"jetpack-related-posts":[{"id":366,"url":"https:\/\/scienceblog.com\/horizon\/366\/digital-age-desperately-needs-ethical-and-legal-guidelines\/","url_meta":{"origin":1508,"position":0},"title":"Digital age ‘desperately’ needs ethical and legal guidelines","author":"Joanna Roberts","date":"July 13, 2018","format":false,"excerpt":"Digital technologies such as artificial intelligence and robotics, \u2018desperately\u2019 need an institutional framework and system of values to help regulate the industry, an ethics expert has told leading scientists and policymakers. Jeroen van den Hoven, professor of ethics and technology at Delft University of Technology in the Netherlands, was speaking\u2026","rel":"","context":"In "Policy"","block_context":{"text":"Policy","link":"https:\/\/scienceblog.com\/horizon\/category\/policy\/"},"img":{"alt_text":"One of the pressing questions that arise with artificial intelligence is how to account for the actions of machines that make decisions by themselves.","src":"https:\/\/i0.wp.com\/scienceblog.com\/horizon\/wp-content\/uploads\/sites\/4\/2018\/07\/sophia_AI_robotcrp.jpg?resize=350%2C200&ssl=1","width":350,"height":200,"srcset":"https:\/\/i0.wp.com\/scienceblog.com\/horizon\/wp-content\/uploads\/sites\/4\/2018\/07\/sophia_AI_robotcrp.jpg?resize=350%2C200&ssl=1 1x, https:\/\/i0.wp.com\/scienceblog.com\/horizon\/wp-content\/uploads\/sites\/4\/2018\/07\/sophia_AI_robotcrp.jpg?resize=525%2C300&ssl=1 1.5x, https:\/\/i0.wp.com\/scienceblog.com\/horizon\/wp-content\/uploads\/sites\/4\/2018\/07\/sophia_AI_robotcrp.jpg?resize=700%2C400&ssl=1 2x, https:\/\/i0.wp.com\/scienceblog.com\/horizon\/wp-content\/uploads\/sites\/4\/2018\/07\/sophia_AI_robotcrp.jpg?resize=1050%2C600&ssl=1 3x, https:\/\/i0.wp.com\/scienceblog.com\/horizon\/wp-content\/uploads\/sites\/4\/2018\/07\/sophia_AI_robotcrp.jpg?resize=1400%2C800&ssl=1 4x"},"classes":[]},{"id":2230,"url":"https:\/\/scienceblog.com\/horizon\/2230\/self-driving-cars-emerge-from-the-sci-fi-realm\/","url_meta":{"origin":1508,"position":1},"title":"Self-driving cars emerge from the sci-fi realm","author":"Horizon Magazine","date":"December 5, 2022","format":false,"excerpt":"Automated-driving technologies are advancing steadily with the promise of reducing road accidents. By\u00a0\u00a0TOM CASSAUWERS It's an ordinary day in the northern German city of Hamburg, where countless cars move along the streets and pedestrians cross at the intersections. Amid all the hustle and bustle, one vehicle advances without the driver's\u2026","rel":"","context":"In "Transport"","block_context":{"text":"Transport","link":"https:\/\/scienceblog.com\/horizon\/category\/transport\/"},"img":{"alt_text":"","src":"https:\/\/i0.wp.com\/scienceblog.com\/horizon\/wp-content\/uploads\/sites\/4\/2022\/12\/5.jpg?resize=350%2C200&ssl=1","width":350,"height":200,"srcset":"https:\/\/i0.wp.com\/scienceblog.com\/horizon\/wp-content\/uploads\/sites\/4\/2022\/12\/5.jpg?resize=350%2C200&ssl=1 1x, https:\/\/i0.wp.com\/scienceblog.com\/horizon\/wp-content\/uploads\/sites\/4\/2022\/12\/5.jpg?resize=525%2C300&ssl=1 1.5x, https:\/\/i0.wp.com\/scienceblog.com\/horizon\/wp-content\/uploads\/sites\/4\/2022\/12\/5.jpg?resize=700%2C400&ssl=1 2x, https:\/\/i0.wp.com\/scienceblog.com\/horizon\/wp-content\/uploads\/sites\/4\/2022\/12\/5.jpg?resize=1050%2C600&ssl=1 3x, https:\/\/i0.wp.com\/scienceblog.com\/horizon\/wp-content\/uploads\/sites\/4\/2022\/12\/5.jpg?resize=1400%2C800&ssl=1 4x"},"classes":[]},{"id":776,"url":"https:\/\/scienceblog.com\/horizon\/776\/can-artificial-intelligence-help-end-fake-news\/","url_meta":{"origin":1508,"position":2},"title":"Can artificial intelligence help end fake news?","author":"Horizon Magazine","date":"April 15, 2019","format":false,"excerpt":"by\u00a0Tom Cassauwers Fake news has already fanned the flames of distrust towards media, politics and established institutions around the world. And while new technologies like artificial intelligence (AI) might make things even worse,\u00a0it can also be used to combat misinformation. Want to make yourself sound like Obama? In the past,\u2026","rel":"","context":"In "Brain & Behavior"","block_context":{"text":"Brain & Behavior","link":"https:\/\/scienceblog.com\/horizon\/category\/brain-behavior\/"},"img":{"alt_text":"Artificial intelligence can be used to create deep fakes - audio, pictures and videos that make people say and do things they never did. Image credit - PxHere","src":"https:\/\/i0.wp.com\/scienceblog.com\/horizon\/wp-content\/uploads\/sites\/4\/2019\/04\/smartphone-woman.jpg?resize=350%2C200&ssl=1","width":350,"height":200,"srcset":"https:\/\/i0.wp.com\/scienceblog.com\/horizon\/wp-content\/uploads\/sites\/4\/2019\/04\/smartphone-woman.jpg?resize=350%2C200&ssl=1 1x, https:\/\/i0.wp.com\/scienceblog.com\/horizon\/wp-content\/uploads\/sites\/4\/2019\/04\/smartphone-woman.jpg?resize=525%2C300&ssl=1 1.5x, https:\/\/i0.wp.com\/scienceblog.com\/horizon\/wp-content\/uploads\/sites\/4\/2019\/04\/smartphone-woman.jpg?resize=700%2C400&ssl=1 2x, https:\/\/i0.wp.com\/scienceblog.com\/horizon\/wp-content\/uploads\/sites\/4\/2019\/04\/smartphone-woman.jpg?resize=1050%2C600&ssl=1 3x, https:\/\/i0.wp.com\/scienceblog.com\/horizon\/wp-content\/uploads\/sites\/4\/2019\/04\/smartphone-woman.jpg?resize=1400%2C800&ssl=1 4x"},"classes":[]},{"id":247,"url":"https:\/\/scienceblog.com\/horizon\/247\/we-want-to-end-the-de-industrialisation-of-europe-prof-jurgen-ruttgers\/","url_meta":{"origin":1508,"position":3},"title":"We want to end the de-industrialisation of Europe \u2013 Prof. J\u00fcrgen R\u00fcttgers","author":"Rex Merrifield","date":"April 24, 2018","format":false,"excerpt":"Artificial intelligence (AI) and\u00a0cyber security\u00a0should be priorities in future EU industrial research policy in order to reinvigorate industry and recover jobs that have been lost abroad, according to Professor J\u00fcrgen R\u00fcttgers, a former research minister in Germany. He leads the\u00a0High Level\u00a0Group on Industrial Technologies, which on 24 April releases a\u2026","rel":"","context":"In "Earth, Energy & Environment"","block_context":{"text":"Earth, Energy & Environment","link":"https:\/\/scienceblog.com\/horizon\/category\/earth-energy-environment\/"},"img":{"alt_text":"Prof. R\u00fcttgers says that one of the great challenges in the 21st century is the transition from the industrial society to the knowledge society. Image credit - Pexels, licensed under CC0","src":"https:\/\/i0.wp.com\/scienceblog.com\/horizon\/wp-content\/uploads\/sites\/4\/2018\/04\/chemical-construction-decay-416348.jpg?resize=350%2C200&ssl=1","width":350,"height":200,"srcset":"https:\/\/i0.wp.com\/scienceblog.com\/horizon\/wp-content\/uploads\/sites\/4\/2018\/04\/chemical-construction-decay-416348.jpg?resize=350%2C200&ssl=1 1x, https:\/\/i0.wp.com\/scienceblog.com\/horizon\/wp-content\/uploads\/sites\/4\/2018\/04\/chemical-construction-decay-416348.jpg?resize=525%2C300&ssl=1 1.5x, https:\/\/i0.wp.com\/scienceblog.com\/horizon\/wp-content\/uploads\/sites\/4\/2018\/04\/chemical-construction-decay-416348.jpg?resize=700%2C400&ssl=1 2x, https:\/\/i0.wp.com\/scienceblog.com\/horizon\/wp-content\/uploads\/sites\/4\/2018\/04\/chemical-construction-decay-416348.jpg?resize=1050%2C600&ssl=1 3x, https:\/\/i0.wp.com\/scienceblog.com\/horizon\/wp-content\/uploads\/sites\/4\/2018\/04\/chemical-construction-decay-416348.jpg?resize=1400%2C800&ssl=1 4x"},"classes":[]},{"id":961,"url":"https:\/\/scienceblog.com\/horizon\/961\/ai-can-help-us-fight-climate-change-but-it-has-an-energy-problem-too\/","url_meta":{"origin":1508,"position":4},"title":"AI can help us fight climate change. But it has an energy problem, too","author":"Horizon Magazine","date":"September 12, 2019","format":false,"excerpt":"by Annette Ekin Artificial intelligence (AI) technology can help us fight climate change \u2013 but it also comes at a cost to the planet. To truly benefit from the technology\u2019s climate solutions, we also need a better understanding of AI\u2019s growing carbon footprint, say researchers.\u00a0\u00a0 AI is changing the way\u2026","rel":"","context":"In "Earth, Energy & Environment"","block_context":{"text":"Earth, Energy & Environment","link":"https:\/\/scienceblog.com\/horizon\/category\/earth-energy-environment\/"},"img":{"alt_text":"Data centres that store and process algorithms use a lot of energy but there is little discussion about their environmental impact. Image credit - 123net\/Wikimedia, licensed under CC BY-SA 3.0","src":"https:\/\/i0.wp.com\/scienceblog.com\/horizon\/wp-content\/uploads\/sites\/4\/2019\/09\/Datacentre2.jpg?resize=350%2C200&ssl=1","width":350,"height":200,"srcset":"https:\/\/i0.wp.com\/scienceblog.com\/horizon\/wp-content\/uploads\/sites\/4\/2019\/09\/Datacentre2.jpg?resize=350%2C200&ssl=1 1x, https:\/\/i0.wp.com\/scienceblog.com\/horizon\/wp-content\/uploads\/sites\/4\/2019\/09\/Datacentre2.jpg?resize=525%2C300&ssl=1 1.5x, https:\/\/i0.wp.com\/scienceblog.com\/horizon\/wp-content\/uploads\/sites\/4\/2019\/09\/Datacentre2.jpg?resize=700%2C400&ssl=1 2x"},"classes":[]},{"id":754,"url":"https:\/\/scienceblog.com\/horizon\/754\/trusting-self-driving-cars-is-going-to-be-a-big-step-for-people\/","url_meta":{"origin":1508,"position":5},"title":"\u2018Trusting self-driving cars is going to be a big step for people\u2019","author":"Horizon Magazine","date":"April 2, 2019","format":false,"excerpt":"Self-driving cars are set to bring one of the biggest changes to our global transportation system in decades, but their potential to increase road safety should not be over-emphasised if we want to increase people\u2019s trust in automated vehicles, says Dr Jean-Fran\u00e7ois Bonnefon from the Toulouse School of Economics, France,\u2026","rel":"","context":"In "Technology"","block_context":{"text":"Technology","link":"https:\/\/scienceblog.com\/horizon\/category\/technology\/"},"img":{"alt_text":"When self-driving cars start to operate in a real-life context, it could be transformative for people's perception of autonomous driving, says Dr Bonnefon.","src":"https:\/\/i0.wp.com\/scienceblog.com\/horizon\/wp-content\/uploads\/sites\/4\/2019\/04\/5554433852_ca581d33d0_o.jpg?resize=350%2C200&ssl=1","width":350,"height":200,"srcset":"https:\/\/i0.wp.com\/scienceblog.com\/horizon\/wp-content\/uploads\/sites\/4\/2019\/04\/5554433852_ca581d33d0_o.jpg?resize=350%2C200&ssl=1 1x, https:\/\/i0.wp.com\/scienceblog.com\/horizon\/wp-content\/uploads\/sites\/4\/2019\/04\/5554433852_ca581d33d0_o.jpg?resize=525%2C300&ssl=1 1.5x, https:\/\/i0.wp.com\/scienceblog.com\/horizon\/wp-content\/uploads\/sites\/4\/2019\/04\/5554433852_ca581d33d0_o.jpg?resize=700%2C400&ssl=1 2x, https:\/\/i0.wp.com\/scienceblog.com\/horizon\/wp-content\/uploads\/sites\/4\/2019\/04\/5554433852_ca581d33d0_o.jpg?resize=1050%2C600&ssl=1 3x, https:\/\/i0.wp.com\/scienceblog.com\/horizon\/wp-content\/uploads\/sites\/4\/2019\/04\/5554433852_ca581d33d0_o.jpg?resize=1400%2C800&ssl=1 4x"},"classes":[]}],"_links":{"self":[{"href":"https:\/\/scienceblog.com\/horizon\/wp-json\/wp\/v2\/posts\/1508","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/scienceblog.com\/horizon\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/scienceblog.com\/horizon\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/scienceblog.com\/horizon\/wp-json\/wp\/v2\/users\/298"}],"replies":[{"embeddable":true,"href":"https:\/\/scienceblog.com\/horizon\/wp-json\/wp\/v2\/comments?post=1508"}],"version-history":[{"count":0,"href":"https:\/\/scienceblog.com\/horizon\/wp-json\/wp\/v2\/posts\/1508\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/scienceblog.com\/horizon\/wp-json\/wp\/v2\/media\/1509"}],"wp:attachment":[{"href":"https:\/\/scienceblog.com\/horizon\/wp-json\/wp\/v2\/media?parent=1508"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/scienceblog.com\/horizon\/wp-json\/wp\/v2\/categories?post=1508"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/scienceblog.com\/horizon\/wp-json\/wp\/v2\/tags?post=1508"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}