{"id":6414,"date":"2021-07-08T18:29:22","date_gmt":"2021-07-08T18:29:22","guid":{"rendered":"http:\/\/TheNextWeb=1359832"},"modified":"2021-07-08T18:29:22","modified_gmt":"2021-07-08T18:29:22","slug":"scientists-created-an-ai-system-that-classifies-thousands-of-galaxies-in-seconds","status":"publish","type":"post","link":"https:\/\/www.londonchiropracter.com\/?p=6414","title":{"rendered":"Scientists created an AI system that classifies thousands of galaxies in seconds"},"content":{"rendered":"\n<div><img decoding=\"async\" src=\"https:\/\/img-cdn.tnwcdn.com\/image\/neural?filter_last=1&amp;fit=1280%2C640&amp;url=https%3A%2F%2Fcdn0.tnwcdn.com%2Fwp-content%2Fblogs.dir%2F1%2Ffiles%2F2021%2F07%2FUntitled-design-11.jpg&amp;signature=8733df73011b669830a09be84dd7fbe3\" class=\"ff-og-image-inserted\"><\/div>\n<p>Scientists have developed an AI system that can classify tens of thousands of galaxies in a few seconds, a process that can take months to do manually.<\/p>\n<p><strong>Up front: <\/strong>Astronomers classify galaxies by shape to understand how they form and evolve. But this can be a time-consuming job.<\/p>\n<p>The researchers used convolutional neural network (CNN) architectures to hasten the task.<\/p>\n<p>Per <a href=\"https:\/\/arxiv.org\/pdf\/2106.01571.pdf\" target=\"_blank\" rel=\"nofollow noopener noreferrer\">the preprint paper<\/a>:<\/p>\n<blockquote readability=\"11\">\n<p>The key strengths of automated classification techniques, such as our CNN approach, ultimately lie in their speed and ability to generalise. Although training a CNN can be a computationally expensive undertaking, the speed with which it can classify galaxies once trained is orders of magnitude greater than what could ever be possible with manual classification.<\/p>\n<\/blockquote>\n<p>The team developed a CNN architecture that outperforms existing models in classifying the morphologies of galaxies in both 3-class (elliptical, lenticular, spiral) and 4-class (+irregular\/miscellaneous) schema. Its overall classification accuracies were 83% and 81% respectively.<\/p>\n<p>They say it will be able to&nbsp;classify more than 100,000,000 galaxies at different distances from Earth and in different environments.<\/p>\n<p><strong>Quick take: <\/strong>The main advantage of using AI to classify galaxies is speed.<\/p>\n<p><span>But lead study author Mitchell Cavanagh, a PhD student at the International Centre for Radio Astronomy Research (ICRAR), said the accuracy is also improving:<\/span><\/p>\n<blockquote readability=\"11\">\n<p>These neural networks are not necessarily going to be better than people because they\u2019re trained by people, but they\u2019re getting close with more than 80% accuracy, and up to 97% when classifying between ellipticals and spirals.&nbsp;<span>If you place a group of astronomers into a room and ask them to classify a bunch of images, there will almost certainly be disagreements. This inherent uncertainty is the limiting factor in any AI model trained on labelled data.<\/span><\/p>\n<\/blockquote>\n<p>Ultimately, the technique could deepen our understanding of how galaxies transform over time.&nbsp;<span>Cavanagh says it could&nbsp;<\/span>even shed light on the nature of the universe itself.<\/p>\n<p> <a href=\"https:\/\/thenextweb.com\/news\/scientists-created-an-ai-system-that-classifies-thousands-of-galaxies-in-seconds\">Source<\/a><\/p>\n","protected":false},"excerpt":{"rendered":"<p>Scientists have developed an AI system that can classify tens of thousands of galaxies in a few seconds, a process that can take months to do manually. Up front: Astronomers classify galaxies&#8230;<\/p>\n","protected":false},"author":1,"featured_media":6415,"comment_status":"open","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":[],"categories":[1],"tags":[],"_links":{"self":[{"href":"https:\/\/www.londonchiropracter.com\/index.php?rest_route=\/wp\/v2\/posts\/6414"}],"collection":[{"href":"https:\/\/www.londonchiropracter.com\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.londonchiropracter.com\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.londonchiropracter.com\/index.php?rest_route=\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/www.londonchiropracter.com\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=6414"}],"version-history":[{"count":0,"href":"https:\/\/www.londonchiropracter.com\/index.php?rest_route=\/wp\/v2\/posts\/6414\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.londonchiropracter.com\/index.php?rest_route=\/wp\/v2\/media\/6415"}],"wp:attachment":[{"href":"https:\/\/www.londonchiropracter.com\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=6414"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.londonchiropracter.com\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=6414"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.londonchiropracter.com\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=6414"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}