{"id":30362,"date":"2026-01-20T18:56:29","date_gmt":"2026-01-20T18:56:29","guid":{"rendered":"https:\/\/techgolly.com\/?p=30362"},"modified":"2026-01-20T18:56:29","modified_gmt":"2026-01-20T18:56:29","slug":"new-in-physics-computing-uses-radio-waves-to-run-ai-on-small-devices","status":"publish","type":"post","link":"https:\/\/techgolly.com\/news\/new-in-physics-computing-uses-radio-waves-to-run-ai-on-small-devices","title":{"rendered":"New &#8216;In-Physics&#8217; Computing Uses Radio Waves to Run AI on Small Devices"},"content":{"rendered":"\n<h3 class=\"wp-block-heading\">Key Points<\/h3>\n\n\n\n<ul class=\"wp-block-list\">\n<li>Researchers have developed a new method, WISE, for running AI on small, battery-powered devices.<\/li>\n\n\n\n<li>The method uses &#8220;in-physics analog computing,&#8221; where radio waves perform part of the AI calculation.<\/li>\n\n\n\n<li>A base station broadcasts the AI model&#8217;s weights, and a simple device mixes them with its own data.<\/li>\n\n\n\n<li>The technology could be used in drones, cameras, and other smart sensors.<\/li>\n<\/ul>\n\n\n\n<p class=\"wp-block-paragraph\">Researchers at Duke University have developed a novel way to run powerful artificial intelligence on small, battery-powered devices like drones and sensors. The new method, called Wireless Smart Edge networks (WISE), uses radio waves to perform much of the heavy lifting, which could solve a major bottleneck in the field of edge computing.<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">The problem with running AI on small devices is that the hardware is tiny, but the AI models are huge. Engineers typically face two undesirable options: they can try to cram the entire AI model onto the device, which drains the battery and requires a lot of memory, or they can send all the data to the cloud for processing, which is slow and can be a security risk.<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">The Duke team proposes a third option, which they call &#8220;in-physics analog computing.&#8221; Instead of sending a stream of ones and zeros back and forth, the radio waves themselves are used to perform a key part of the AI calculation.<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">Here&#8217;s how it works: a nearby base station stores the full AI model and broadcasts a radio signal that contains the model&#8217;s &#8220;weights&#8221;\u2014the numbers needed to do the math. <\/p>\n\n\n\n<p class=\"wp-block-paragraph\">When that signal reaches a device, a simple piece of hardware mixes it with the device&#8217;s own data, such as a camera feed. This mixing process naturally performs a crucial step in most AI models, without needing a powerful digital processor.<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">&#8220;We&#8217;re taking advantage of computations that common, miniaturized electronics already give us,&#8221; said Tingjun Chen, the lead researcher on the project.<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">Because the device doesn&#8217;t have to store the entire model or run it digitally, it saves substantial energy and memory. This could be transformative for a range of applications, from smart traffic sensors to autonomous drones, enabling them to run much more advanced AI models than they can today.<\/p>\n\n\n\n<p class=\"wp-block-paragraph\"><strong>Source: <\/strong><em><a href=\"https:\/\/www.science.org\/doi\/10.1126\/sciadv.adz0817\" data-type=\"link\" data-id=\"https:\/\/www.science.org\/doi\/10.1126\/sciadv.adz0817\" target=\"_blank\" rel=\"noopener\">Science Advances<\/a><\/em>\u00a0(2026).<\/p>\n","protected":false},"excerpt":{"rendered":"<p>Key Points Researchers at Duke University have developed a novel way to run powerful artificial intelligence on small, battery-powered devices like drones and sensors. The&hellip;<\/p>\n","protected":false},"author":1,"featured_media":30363,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[50],"tags":[],"class_list":["post-30362","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-research"],"_links":{"self":[{"href":"https:\/\/techgolly.com\/news\/wp-json\/wp\/v2\/posts\/30362","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/techgolly.com\/news\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/techgolly.com\/news\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/techgolly.com\/news\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/techgolly.com\/news\/wp-json\/wp\/v2\/comments?post=30362"}],"version-history":[{"count":0,"href":"https:\/\/techgolly.com\/news\/wp-json\/wp\/v2\/posts\/30362\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/techgolly.com\/news\/wp-json\/wp\/v2\/media\/30363"}],"wp:attachment":[{"href":"https:\/\/techgolly.com\/news\/wp-json\/wp\/v2\/media?parent=30362"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/techgolly.com\/news\/wp-json\/wp\/v2\/categories?post=30362"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/techgolly.com\/news\/wp-json\/wp\/v2\/tags?post=30362"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}