{"id":661442,"date":"2025-07-28T10:18:05","date_gmt":"2025-07-28T14:18:05","guid":{"rendered":"https:\/\/www.rochester.edu\/newscenter\/?p=661442"},"modified":"2025-07-28T10:18:05","modified_gmt":"2025-07-28T14:18:05","slug":"predictive-coding-networks-autonomous-systems-661442","status":"publish","type":"post","link":"https:\/\/www.rochester.edu\/newscenter\/predictive-coding-networks-autonomous-systems-661442\/","title":{"rendered":"How brain-inspired analog systems could make drones more efficient"},"content":{"rendered":"

Electrical and computer engineers want to mimic the brain\u2019s visual system to create AI tools for guiding autonomous systems.<\/strong><\/h2>\n

The artificial intelligence systems that guide drones and self-driving cars rely on neural networks\u2014trainable computing systems inspired by the human brain. But the digital computers they run on were initially designed for general-purpose computing tasks ranging from word processing to scientific calculations and have ultra-high reliability at the expense of high-power consumption.<\/p>\n

To explore novel computer systems that are energy efficient particularly for machine learning, engineers at the University of Rochester<\/a> are developing new analog hardware, with the possible application toward more efficient drones. Rochester engineers are attempting to do so by abandoning conventional state-of-the-art neural networks developed on digital hardware for computer vision. Instead, they\u2019re turning to predictive coding networks, which are based on neuroscience theories that the brain has a mental model of the environment and constantly updates it based on feedback from the eyes.<\/p>\n

\u201cResearch by neuroscientists has shown that the workhorse of developing neural networks\u2014this mechanism called back propagation\u2014is biologically implausible and our brains\u2019 perception systems don\u2019t work that way,\u201d says Michael Huang<\/a>, a professor of electrical and computer engineering<\/a>, of computer science<\/a>, and of data science and artificial intelligence<\/a> at Rochester. \u201cTo solve the problem, we asked how our brains do it. The prevailing theory is predictive coding, which involves a hierarchical process of prediction and correction\u2014think paraphrasing what you heard, telling it to the speaker, and using their feedback to refine your understanding.\u201d<\/p>\n

Huang notes that the University of Rochester has a rich history in computer vision research and that the late computer science professor Dana Ballard was an author on one of the earliest, most influential papers on predicative coding networks<\/a>.<\/p>\n

The Rochester-led team includes Huang and electrical and computer engineering professors Hui Wu<\/a> and Tong Geng<\/a>, their students, as well as two research groups from Rice University and UCLA. The team will receive up to $7.2 million from the Defense Advanced Research Projects Agency (DARPA) over the next 54 months to develop biologically inspired predictive coding networks for digital image recognition built on analog circuits. While the initial prototype will look at classifying static images, if they can get the analog system to approach the performance of existing digital approaches, they believe it can be translated to more complex perception tasks needed by self-driving cars and autonomous drones.<\/p>\n

And while the approach is novel, the system will not use any experimental devices but will instead be manufactured using existing technologies like the complementary metal oxide semiconductor (CMOS).<\/p>\n","protected":false},"excerpt":{"rendered":"

Electrical and computer engineers want to mimic the brain\u2019s visual system to create AI tools for guiding autonomous systems.<\/p>\n","protected":false},"author":1242,"featured_media":661482,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"_acf_changed":false,"footnotes":""},"categories":[116],"tags":[24292,18802,19382,25592,18632,41992,41982,9186,42002],"class_list":["post-661442","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-sci-tech","tag-artificial-intelligence","tag-department-of-computer-science","tag-department-of-electrical-and-computer-engineering","tag-goergen-institute-for-data-science-and-artificial-intelligence","tag-hajim-school-of-engineering-and-applied-sciences","tag-hui-wu","tag-michael-huang","tag-research-funding","tag-tong-geng"],"acf":[],"yoast_head":"\nHow brain-inspired analog systems could make drones more efficient<\/title>\n<meta name=\"description\" content=\"Using predictive coding, University of Rochester engineers aim to mimic the brain\u2019s visual system to create AI tools for autonomous systems.\" \/>\n<meta name=\"robots\" content=\"index, follow, max-snippet:-1, max-image-preview:large, max-video-preview:-1\" \/>\n<link rel=\"canonical\" href=\"https:\/\/www.rochester.edu\/newscenter\/predictive-coding-networks-autonomous-systems-661442\/\" \/>\n<meta property=\"og:locale\" content=\"en_US\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"How brain-inspired analog systems could make drones more efficient\" \/>\n<meta property=\"og:description\" content=\"Using predictive coding, University of Rochester engineers aim to mimic the brain\u2019s visual system to create AI tools for autonomous systems.\" \/>\n<meta property=\"og:url\" content=\"https:\/\/www.rochester.edu\/newscenter\/predictive-coding-networks-autonomous-systems-661442\/\" \/>\n<meta property=\"og:site_name\" content=\"News Center\" \/>\n<meta property=\"article:published_time\" content=\"2025-07-28T14:18:05+00:00\" \/>\n<meta property=\"og:image\" content=\"https:\/\/www.rochester.edu\/newscenter\/wp-content\/uploads\/2025\/07\/fea-predictive-coding-networks-autonomous-systems-GettyImages-1359211769-copy-1200x630.jpg\" \/>\n\t<meta property=\"og:image:width\" content=\"1200\" \/>\n\t<meta property=\"og:image:height\" content=\"630\" \/>\n\t<meta property=\"og:image:type\" content=\"image\/jpeg\" \/>\n<meta name=\"author\" content=\"Luke Auburn\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:label1\" content=\"Written by\" \/>\n\t<meta name=\"twitter:data1\" content=\"Luke Auburn\" \/>\n\t<meta name=\"twitter:label2\" content=\"Est. reading time\" \/>\n\t<meta name=\"twitter:data2\" content=\"3 minutes\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\\\/\\\/schema.org\",\"@graph\":[{\"@type\":\"Article\",\"@id\":\"https:\\\/\\\/www.rochester.edu\\\/newscenter\\\/predictive-coding-networks-autonomous-systems-661442\\\/#article\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/www.rochester.edu\\\/newscenter\\\/predictive-coding-networks-autonomous-systems-661442\\\/\"},\"author\":{\"name\":\"Luke Auburn\",\"@id\":\"https:\\\/\\\/www.rochester.edu\\\/newscenter\\\/#\\\/schema\\\/person\\\/e928dc2863b53a89ece6d40c7992a4e1\"},\"headline\":\"How brain-inspired analog systems could make drones more efficient\",\"datePublished\":\"2025-07-28T14:18:05+00:00\",\"mainEntityOfPage\":{\"@id\":\"https:\\\/\\\/www.rochester.edu\\\/newscenter\\\/predictive-coding-networks-autonomous-systems-661442\\\/\"},\"wordCount\":438,\"image\":{\"@id\":\"https:\\\/\\\/www.rochester.edu\\\/newscenter\\\/predictive-coding-networks-autonomous-systems-661442\\\/#primaryimage\"},\"thumbnailUrl\":\"https:\\\/\\\/www.rochester.edu\\\/newscenter\\\/wp-content\\\/uploads\\\/2025\\\/07\\\/fea-predictive-coding-networks-autonomous-systems-GettyImages-1359211769-copy.jpg\",\"keywords\":[\"artificial intelligence\",\"Department of Computer Science\",\"Department of Electrical and Computer Engineering\",\"Goergen Institute for Data Science and Artificial Intelligence\",\"Hajim School of Engineering and Applied Sciences\",\"Hui Wu\",\"Michael Huang\",\"research funding\",\"Tong Geng\"],\"articleSection\":[\"Science & Technology\"],\"inLanguage\":\"en-US\"},{\"@type\":\"WebPage\",\"@id\":\"https:\\\/\\\/www.rochester.edu\\\/newscenter\\\/predictive-coding-networks-autonomous-systems-661442\\\/\",\"url\":\"https:\\\/\\\/www.rochester.edu\\\/newscenter\\\/predictive-coding-networks-autonomous-systems-661442\\\/\",\"name\":\"How brain-inspired analog systems could make drones more efficient\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/www.rochester.edu\\\/newscenter\\\/#website\"},\"primaryImageOfPage\":{\"@id\":\"https:\\\/\\\/www.rochester.edu\\\/newscenter\\\/predictive-coding-networks-autonomous-systems-661442\\\/#primaryimage\"},\"image\":{\"@id\":\"https:\\\/\\\/www.rochester.edu\\\/newscenter\\\/predictive-coding-networks-autonomous-systems-661442\\\/#primaryimage\"},\"thumbnailUrl\":\"https:\\\/\\\/www.rochester.edu\\\/newscenter\\\/wp-content\\\/uploads\\\/2025\\\/07\\\/fea-predictive-coding-networks-autonomous-systems-GettyImages-1359211769-copy.jpg\",\"datePublished\":\"2025-07-28T14:18:05+00:00\",\"author\":{\"@id\":\"https:\\\/\\\/www.rochester.edu\\\/newscenter\\\/#\\\/schema\\\/person\\\/e928dc2863b53a89ece6d40c7992a4e1\"},\"description\":\"Using predictive coding, University of Rochester engineers aim to mimic the brain\u2019s visual system to create AI tools for autonomous systems.\",\"breadcrumb\":{\"@id\":\"https:\\\/\\\/www.rochester.edu\\\/newscenter\\\/predictive-coding-networks-autonomous-systems-661442\\\/#breadcrumb\"},\"inLanguage\":\"en-US\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\\\/\\\/www.rochester.edu\\\/newscenter\\\/predictive-coding-networks-autonomous-systems-661442\\\/\"]}]},{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\\\/\\\/www.rochester.edu\\\/newscenter\\\/predictive-coding-networks-autonomous-systems-661442\\\/#primaryimage\",\"url\":\"https:\\\/\\\/www.rochester.edu\\\/newscenter\\\/wp-content\\\/uploads\\\/2025\\\/07\\\/fea-predictive-coding-networks-autonomous-systems-GettyImages-1359211769-copy.jpg\",\"contentUrl\":\"https:\\\/\\\/www.rochester.edu\\\/newscenter\\\/wp-content\\\/uploads\\\/2025\\\/07\\\/fea-predictive-coding-networks-autonomous-systems-GettyImages-1359211769-copy.jpg\",\"width\":2000,\"height\":1200,\"caption\":\"NEXT-GEN DRONES: To explore novel computer systems that are more energy efficient, University of Rochester engineers are developing new analog hardware using predictive coding networks. (Getty Images photo)\"},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\\\/\\\/www.rochester.edu\\\/newscenter\\\/predictive-coding-networks-autonomous-systems-661442\\\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Home\",\"item\":\"https:\\\/\\\/www.rochester.edu\\\/newscenter\\\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"How brain-inspired analog systems could make drones more efficient\"}]},{\"@type\":\"WebSite\",\"@id\":\"https:\\\/\\\/www.rochester.edu\\\/newscenter\\\/#website\",\"url\":\"https:\\\/\\\/www.rochester.edu\\\/newscenter\\\/\",\"name\":\"News Center\",\"description\":\"University of Rochester\",\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\\\/\\\/www.rochester.edu\\\/newscenter\\\/?s={search_term_string}\"},\"query-input\":{\"@type\":\"PropertyValueSpecification\",\"valueRequired\":true,\"valueName\":\"search_term_string\"}}],\"inLanguage\":\"en-US\"},{\"@type\":\"Person\",\"@id\":\"https:\\\/\\\/www.rochester.edu\\\/newscenter\\\/#\\\/schema\\\/person\\\/e928dc2863b53a89ece6d40c7992a4e1\",\"name\":\"Luke Auburn\",\"url\":\"https:\\\/\\\/www.rochester.edu\\\/newscenter\\\/author\\\/lauburn\\\/\"}]}<\/script>\n<!-- \/ Yoast SEO plugin. -->","yoast_head_json":{"title":"How brain-inspired analog systems could make drones more efficient","description":"Using predictive coding, University of Rochester engineers aim to mimic the brain\u2019s visual system to create AI tools for autonomous systems.","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:\/\/www.rochester.edu\/newscenter\/predictive-coding-networks-autonomous-systems-661442\/","og_locale":"en_US","og_type":"article","og_title":"How brain-inspired analog systems could make drones more efficient","og_description":"Using predictive coding, University of Rochester engineers aim to mimic the brain\u2019s visual system to create AI tools for autonomous systems.","og_url":"https:\/\/www.rochester.edu\/newscenter\/predictive-coding-networks-autonomous-systems-661442\/","og_site_name":"News Center","article_published_time":"2025-07-28T14:18:05+00:00","og_image":[{"width":1200,"height":630,"url":"https:\/\/www.rochester.edu\/newscenter\/wp-content\/uploads\/2025\/07\/fea-predictive-coding-networks-autonomous-systems-GettyImages-1359211769-copy-1200x630.jpg","type":"image\/jpeg"}],"author":"Luke Auburn","twitter_card":"summary_large_image","twitter_misc":{"Written by":"Luke Auburn","Est. reading time":"3 minutes"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"Article","@id":"https:\/\/www.rochester.edu\/newscenter\/predictive-coding-networks-autonomous-systems-661442\/#article","isPartOf":{"@id":"https:\/\/www.rochester.edu\/newscenter\/predictive-coding-networks-autonomous-systems-661442\/"},"author":{"name":"Luke Auburn","@id":"https:\/\/www.rochester.edu\/newscenter\/#\/schema\/person\/e928dc2863b53a89ece6d40c7992a4e1"},"headline":"How brain-inspired analog systems could make drones more efficient","datePublished":"2025-07-28T14:18:05+00:00","mainEntityOfPage":{"@id":"https:\/\/www.rochester.edu\/newscenter\/predictive-coding-networks-autonomous-systems-661442\/"},"wordCount":438,"image":{"@id":"https:\/\/www.rochester.edu\/newscenter\/predictive-coding-networks-autonomous-systems-661442\/#primaryimage"},"thumbnailUrl":"https:\/\/www.rochester.edu\/newscenter\/wp-content\/uploads\/2025\/07\/fea-predictive-coding-networks-autonomous-systems-GettyImages-1359211769-copy.jpg","keywords":["artificial intelligence","Department of Computer Science","Department of Electrical and Computer Engineering","Goergen Institute for Data Science and Artificial Intelligence","Hajim School of Engineering and Applied Sciences","Hui Wu","Michael Huang","research funding","Tong Geng"],"articleSection":["Science & Technology"],"inLanguage":"en-US"},{"@type":"WebPage","@id":"https:\/\/www.rochester.edu\/newscenter\/predictive-coding-networks-autonomous-systems-661442\/","url":"https:\/\/www.rochester.edu\/newscenter\/predictive-coding-networks-autonomous-systems-661442\/","name":"How brain-inspired analog systems could make drones more efficient","isPartOf":{"@id":"https:\/\/www.rochester.edu\/newscenter\/#website"},"primaryImageOfPage":{"@id":"https:\/\/www.rochester.edu\/newscenter\/predictive-coding-networks-autonomous-systems-661442\/#primaryimage"},"image":{"@id":"https:\/\/www.rochester.edu\/newscenter\/predictive-coding-networks-autonomous-systems-661442\/#primaryimage"},"thumbnailUrl":"https:\/\/www.rochester.edu\/newscenter\/wp-content\/uploads\/2025\/07\/fea-predictive-coding-networks-autonomous-systems-GettyImages-1359211769-copy.jpg","datePublished":"2025-07-28T14:18:05+00:00","author":{"@id":"https:\/\/www.rochester.edu\/newscenter\/#\/schema\/person\/e928dc2863b53a89ece6d40c7992a4e1"},"description":"Using predictive coding, University of Rochester engineers aim to mimic the brain\u2019s visual system to create AI tools for autonomous systems.","breadcrumb":{"@id":"https:\/\/www.rochester.edu\/newscenter\/predictive-coding-networks-autonomous-systems-661442\/#breadcrumb"},"inLanguage":"en-US","potentialAction":[{"@type":"ReadAction","target":["https:\/\/www.rochester.edu\/newscenter\/predictive-coding-networks-autonomous-systems-661442\/"]}]},{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/www.rochester.edu\/newscenter\/predictive-coding-networks-autonomous-systems-661442\/#primaryimage","url":"https:\/\/www.rochester.edu\/newscenter\/wp-content\/uploads\/2025\/07\/fea-predictive-coding-networks-autonomous-systems-GettyImages-1359211769-copy.jpg","contentUrl":"https:\/\/www.rochester.edu\/newscenter\/wp-content\/uploads\/2025\/07\/fea-predictive-coding-networks-autonomous-systems-GettyImages-1359211769-copy.jpg","width":2000,"height":1200,"caption":"NEXT-GEN DRONES: To explore novel computer systems that are more energy efficient, University of Rochester engineers are developing new analog hardware using predictive coding networks. (Getty Images photo)"},{"@type":"BreadcrumbList","@id":"https:\/\/www.rochester.edu\/newscenter\/predictive-coding-networks-autonomous-systems-661442\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https:\/\/www.rochester.edu\/newscenter\/"},{"@type":"ListItem","position":2,"name":"How brain-inspired analog systems could make drones more efficient"}]},{"@type":"WebSite","@id":"https:\/\/www.rochester.edu\/newscenter\/#website","url":"https:\/\/www.rochester.edu\/newscenter\/","name":"News Center","description":"University of Rochester","potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/www.rochester.edu\/newscenter\/?s={search_term_string}"},"query-input":{"@type":"PropertyValueSpecification","valueRequired":true,"valueName":"search_term_string"}}],"inLanguage":"en-US"},{"@type":"Person","@id":"https:\/\/www.rochester.edu\/newscenter\/#\/schema\/person\/e928dc2863b53a89ece6d40c7992a4e1","name":"Luke Auburn","url":"https:\/\/www.rochester.edu\/newscenter\/author\/lauburn\/"}]}},"_links":{"self":[{"href":"https:\/\/www.rochester.edu\/newscenter\/wp-json\/wp\/v2\/posts\/661442","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.rochester.edu\/newscenter\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.rochester.edu\/newscenter\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.rochester.edu\/newscenter\/wp-json\/wp\/v2\/users\/1242"}],"replies":[{"embeddable":true,"href":"https:\/\/www.rochester.edu\/newscenter\/wp-json\/wp\/v2\/comments?post=661442"}],"version-history":[{"count":4,"href":"https:\/\/www.rochester.edu\/newscenter\/wp-json\/wp\/v2\/posts\/661442\/revisions"}],"predecessor-version":[{"id":661502,"href":"https:\/\/www.rochester.edu\/newscenter\/wp-json\/wp\/v2\/posts\/661442\/revisions\/661502"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.rochester.edu\/newscenter\/wp-json\/wp\/v2\/media\/661482"}],"wp:attachment":[{"href":"https:\/\/www.rochester.edu\/newscenter\/wp-json\/wp\/v2\/media?parent=661442"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.rochester.edu\/newscenter\/wp-json\/wp\/v2\/categories?post=661442"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.rochester.edu\/newscenter\/wp-json\/wp\/v2\/tags?post=661442"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}