![](\"https:\/\/dmn-dallas-news-prod.cdn.arcpublishing.com\/resizer\/v2\/NQ5UR5T64ZC5DA2F5XVYSQ4CHA.jpg?auth=000f476554b2623f0453b4422615456b97184cf3c729694172d91ef49c85f7a5&quality=80&width=250)
\n","protected":false},"excerpt":{"rendered":"As artificial intelligence platforms like OpenAI\u2019s ChatGPT and Microsoft\u2019s Copilot go mainstream, power bills from their usage are exploding. In response, researchers are racing to build hardware that would guzzle less energy. One such effort is underway at the University of Texas at Dallas. Working with Texas Instruments and Arizona-based Everspin Technologies, scientists there have built a small neuromorphic computer system \u2014 a brain-inspired design \u2014 that uses tiny magnetic \u201csandwiches\u201d inside its chips to mimic the behavior of neurons. In lab tests, an AI program running on this hardware recognized tiny black-and-white images while using less circuitry and energy compared to today\u2019s AI systems.<\/p>\n
The findings of this prototype, published in the journal Communications Engineering, are \u201ca tour de force\u201d not just in how AI models run but in how they learn \u2014 the energy-hungry process that teaches these algorithms to make good predictions, said Mark Stiles, a computer scientist at the National Institute of Standards and Technology in Washington, D.C., who was not involved in the study.<\/p>\n
Imitating human brains in computing isn\u2019t a new idea. In the late 1950s, the U.S. Office of Naval Research unveiled the \u201cperceptron,\u201d a 5-ton, room-sized machine that, after about 50 trials, taught itself to identify punch cards marked on either the left or right. The computer relied on a single-layer neural network, an algorithm that learns through trial and error to tell which of two categories an input belongs to.<\/p>\n
Decades later, the perceptron\u2019s design would inspire deep learning, a kind of AI that finds patterns in data by running it through many layers of artificial neurons, also known as nodes. (Each neural layer receives data, processes it and sends it on to the next layer.) Deep learning revolutionized AI and is now commonplace, curating social media feeds, powering image recognition and more.<\/p>\n
But that kind of intelligence, along with other generative AI models, comes with a hefty energy bill. Training OpenAI\u2019s GPT-3, for example, consumes about as much electricity as powering an average U.S. household for 120 years. One estimate says ChatGPT\u2019s daily queries from millions of users use enough energy to charge thousands of electric vehicles a day and power roughly 29,000 U.S. homes for a year.<\/p>\n
Some efforts to slash energy costs focus on using renewable sources, or on slimming down the AI models themselves. But engineers and computer scientists are also looking to neuromorphic computing \u2014 first conceived of in the late 1980s \u2014 as another way to offset AI\u2019s energy boom.<\/p>\n
At UT Dallas, Joseph Friedman, an associate professor of electrical and computer engineering, is making neuromorphic computer chips that process information like human neurons and store it locally, like synapses. Synapses pass a signal to the next neuron and convey how strong that signal is. In the human brain, studies suggest that at least some types of memory are stored in synapses.<\/p>\n
One of the biggest hurdles for the researchers is copying how synapses store the strength of a connection, Friedman said. Signals between neurons in the brain aren\u2019t simply binary \u2014 on or off, like in a conventional computer. Synapses can be stronger or weaker, adjusted like a volume dial on a boombox through different chemicals.<\/p>\n
Joseph Friedman is an associate professor of electrical and computer engineering at the University of Texas at Dallas.<\/p>\n
UT Dallas<\/p>\n
Storing that kind of analog data in computer hardware is messy and error-prone, Friedman said. His team instead uses magnetic tunnel junctions, or tiny magnetic sandwiches made of two magnetic layers separated by a thin barrier. Electrons can travel through that barrier easily when the magnets line up and less so when they point in opposite directions, making each junction act like an on-and-off switch. The overall signal between artificial neurons can be strengthened or weakened by flipping on more or fewer of these switches.<\/p>\n
Friedman and his colleagues wired together eight of these magnetic sandwiches into a prototype computer system running an AI image-recognition model. The black-and-white images they asked the AI to distinguish were simple and small \u2014 just four pixels large, or roughly the size of a speck on a TV screen.<\/p>\n
That task might not seem like much, but when the team pitted the setup against a conventional AI system, it learned the patterns and made predictions with less total energy \u2014 in part because it could store its memory within the neuromorphic chips.<\/p>\n
While the prototype is small, Friedman said that once the neuromorphic system is built at a large scale, \u201cwe\u2019re shooting for on the order of 100 to 1,000 times more energy efficiency\u201d compared with electronic circuits called graphics processing units, such as those produced by California-based tech giant Nvidia.<\/p>\n
Introduction to Neuromorphic Computing As artificial intelligence platforms like OpenAI\u2019s ChatGPT and Microsoft\u2019s Copilot go mainstream, power bills from their usage are exploding. In response, researchers are racing to build hardware that would guzzle less energy. One such effort is underway at the University of Texas at Dallas. Working with Texas Instruments and Arizona-based Everspin […]<\/p>\n","protected":false},"author":12,"featured_media":18192,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"rank_math_lock_modified_date":false,"_jetpack_memberships_contains_paid_content":false,"footnotes":""},"categories":[14],"tags":[],"class_list":{"0":"post-18190","1":"post","2":"type-post","3":"status-publish","4":"format-standard","5":"has-post-thumbnail","7":"category-news"},"jetpack_featured_media_url":"https:\/\/dmn-dallas-news-prod.cdn.arcpublishing.com\/resizer\/v2\/EXMHJNW43BCKJIFBUYUBTTUBCE.jpg?auth=f11ce8f8a92c86ccdba156595aae795c19dca9a54baa66e8162bc383527705c2&quality=80&width=1200&height=630&smart=true","jetpack_sharing_enabled":true,"_links":{"self":[{"href":"https:\/\/citystuff.com\/dallas\/wp-json\/wp\/v2\/posts\/18190"}],"collection":[{"href":"https:\/\/citystuff.com\/dallas\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/citystuff.com\/dallas\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/citystuff.com\/dallas\/wp-json\/wp\/v2\/users\/12"}],"replies":[{"embeddable":true,"href":"https:\/\/citystuff.com\/dallas\/wp-json\/wp\/v2\/comments?post=18190"}],"version-history":[{"count":1,"href":"https:\/\/citystuff.com\/dallas\/wp-json\/wp\/v2\/posts\/18190\/revisions"}],"predecessor-version":[{"id":18193,"href":"https:\/\/citystuff.com\/dallas\/wp-json\/wp\/v2\/posts\/18190\/revisions\/18193"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/citystuff.com\/dallas\/wp-json\/wp\/v2\/media\/18192"}],"wp:attachment":[{"href":"https:\/\/citystuff.com\/dallas\/wp-json\/wp\/v2\/media?parent=18190"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/citystuff.com\/dallas\/wp-json\/wp\/v2\/categories?post=18190"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/citystuff.com\/dallas\/wp-json\/wp\/v2\/tags?post=18190"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}