Adrian E. Bayer<\/a>, the study\u2019s co-author and a cosmologist at the Flatiron Institute and Princeton University, told Gizmodo. \u201cAt the same time, the study is a reminder that acceleration and understanding have to go together.\u201d<\/p>\n The costly truth <\/p>\n
Cosmological breakthroughs tend to be costly and time-consuming. As Dark Energy Spectroscopic Instrument (DESI) co-spokesperson Will Percival told Gizmodo back in April, preparing datasets for scientific analysis involves the creation of mock universes and galaxies and then running simulations as sanity checks. These processes are vital for drawing any serious conclusions from advanced observations.<\/p>\n<\/p>\n
But simulations of models beyond the standard model\u2014extensions that involve massive neutrinos, evolving dark energy, or modified gravity\u2014are also very expensive, Bayer told Gizmodo. At the same time, testing these alternative scenarios, regardless of whether they end up being right, is critical in advancing our understanding of the cosmos. That practical motivation was what led Bayer to look for \u201cmethods that can learn efficiently without requiring huge new simulation suites for every scenario.\u201d<\/p>\n
Bumpy transfers? <\/p>\n
For the experiment, the team used a machine learning strategy called transfer learning. In this approach, a model first learns from one task or dataset\u2014simulations of the standard model\u2014and applies this knowledge to learn a related task or extended versions of the standard model that include promising ideas for new physics.<\/p>\n
According to Bayer, the AI performed quite well in terms of understanding the standard model based on fewer, less costly simulations. However, it began to struggle when new physics \u201coverlaps with directions it has already learned in [the standard model] parameter space,\u201d he noted. This phenomenon, called negative transfer, emerged as the AI became biased and wasn\u2019t able to distinguish between two different physical effects that produce similar patterns in the data. So instead of spotting something inherently new, the AI relied on stuff it had already learned, causing it to miss potential clues that hinted at physics beyond the standard model.<\/p>\n
\u201cThe negative transfer result is fascinating because it shows that the model is not failing randomly,\u201d Bayer added. \u201cUnderstanding when transfer learning helps and when it reinforces those degeneracies is very important for using AI reliably in future cosmological analyses.\u201d<\/p>\n
AI and cosmology <\/p>\n
For Bayer, the latest findings affirm the not-so-novel notion that AI can be helpful, but human experts must carefully follow its calculations to understand and pursue relevant questions.<\/p>\n
\u201cTransfer learning can give AI a powerful head start, allowing us to test many more ideas about the universe than would otherwise be practical,\u201d he said. \u201cBut if a model carries knowledge from one setting into another, we need to understand what it has carried over\u2014when that knowledge helps and when it might mislead.\u201d<\/p>\n
Next, Bayer and colleagues plan to conduct similar experiments in settings that \u201cmore closely resemble actual survey data\u201d that include \u201cgalaxy formation uncertainties, survey masks, and noise.\u201d Additionally, the team wants to explore which cosmological inquiries could benefit most from transfer learning.<\/p>\n","protected":false},"excerpt":{"rendered":"When cosmology makes headlines, we often see fancy images of cosmic maps and supernovas. But in reality, scientists…\n","protected":false},"author":2,"featured_media":730926,"comment_status":"","ping_status":"","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[7],"tags":[3508,49,48,12448,796,66],"class_list":["post-730925","post","type-post","status-publish","format-standard","has-post-thumbnail","category-science","tag-astrophysics","tag-ca","tag-canada","tag-cosmology","tag-machine-learning","tag-science"],"_links":{"self":[{"href":"https:\/\/www.newsbeep.com\/ca\/wp-json\/wp\/v2\/posts\/730925","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.newsbeep.com\/ca\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.newsbeep.com\/ca\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.newsbeep.com\/ca\/wp-json\/wp\/v2\/users\/2"}],"replies":[{"embeddable":true,"href":"https:\/\/www.newsbeep.com\/ca\/wp-json\/wp\/v2\/comments?post=730925"}],"version-history":[{"count":0,"href":"https:\/\/www.newsbeep.com\/ca\/wp-json\/wp\/v2\/posts\/730925\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.newsbeep.com\/ca\/wp-json\/wp\/v2\/media\/730926"}],"wp:attachment":[{"href":"https:\/\/www.newsbeep.com\/ca\/wp-json\/wp\/v2\/media?parent=730925"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.newsbeep.com\/ca\/wp-json\/wp\/v2\/categories?post=730925"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.newsbeep.com\/ca\/wp-json\/wp\/v2\/tags?post=730925"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}