{"id":5808,"date":"2018-10-17T23:59:59","date_gmt":"2018-10-18T06:59:59","guid":{"rendered":"https:\/\/athis-consulting.com\/news\/?p=5808"},"modified":"2018-10-18T00:08:13","modified_gmt":"2018-10-18T07:08:13","slug":"ai-on-a-mems-device-brings-neuromorphic-computing-to-the-edge","status":"publish","type":"post","link":"https:\/\/athis-technologies.com\/news\/innovation\/manufacturing\/2018\/ai-on-a-mems-device-brings-neuromorphic-computing-to-the-edge\/","title":{"rendered":"AI on a MEMS Device Brings Neuromorphic Computing to the Edge"},"content":{"rendered":"<p>In order to achieve the edge computing\u00a0that people talk about in a host of applications including\u00a0<a href=\"https:\/\/spectrum.ieee.org\/tech-talk\/telecom\/wireless\/smartphones-will-get-even-smarter-with-ondevice-machine-learning\">5G networks<\/a>\u00a0and the\u00a0<a href=\"https:\/\/spectrum.ieee.org\/tech-talk\/telecom\/internet\/jeremy-rifkin-on-the-internet-of-things-and-the-next-industrial-revolution\">Internet of Things\u00a0<\/a>(IoT), you need to pack a lot of processing power into comparatively small devices.<\/p>\n<p>The way forward for that idea will be to leverage artificial intelligence (AI) computing techniques\u2014for so-called\u00a0<a href=\"https:\/\/spectrum.ieee.org\/tech-talk\/computing\/embedded-systems\/two-startups-use-processing-in-flash-memory-for-ai-at-the-edge\">AI at the edge<\/a>.\u00a0While some are concerned about how technologists will tackle\u00a0AI for applications beyond traditional computing\u2014and some are wringing their hands over\u00a0<a href=\"https:\/\/spectrum.ieee.org\/tech-talk\/robotics\/artificial-intelligence\/former-head-of-google-china-foresees-an-ai-crisis\">which country will have the upper hand<\/a>\u00a0in this new frontier\u2014the technology is still pretty early in its development cycle.<\/p>\n<p>But it appears that still-too-early-yet status is about to change a bit. Researchers at the Universit\u00e9 de Sherbrooke in Qu\u00e9bec, Canada, have managed to equip a microelectromechanical system (MEMS) device with a form of artificial intelligence, marking the first time that any type of AI has been included in a MEMS device. The result is a kind of\u00a0<a href=\"https:\/\/spectrum.ieee.org\/nanoclast\/semiconductors\/devices\/memtransistor-forms-foundational-circuit-element-to-neuromorphic-computing\">neuromorphic computing<\/a>\u00a0that operates like the human brain\u00a0but\u00a0in\u00a0a microscale device. The combination\u00a0makes\u00a0it possible to process data on the device itself, thus improving\u00a0the prospects for edge computing.<\/p>\n<p>\u201cWe had already written a paper last year showing theoretically that MEMS AI could be done,\u201d said\u00a0<a href=\"https:\/\/www.usherbrooke.ca\/gmecanique\/departement\/corps-professoral\/julien-sylvestre\/\">Julien Sylvestre<\/a>, a professor at Sherbrooke and coauthor of the research paper detailing the advance. \u201cOur latest breakthrough was to demonstrate a device that could do it in the lab.\u201d<\/p>\n<p>The AI method the researchers demonstrated in their research, which is described\u00a0in the\u00a0<em><a href=\"http:\/\/aip.scitation.org\/doi\/full\/10.1063\/1.5038038\">Journal of Applied Physics<\/a>,\u00a0<\/em>is something called \u201c<a href=\"https:\/\/en.wikipedia.org\/wiki\/Reservoir_computing\">reservoir computing<\/a>.\u201d\u00a0Sylvestre explains that to understand a bit about reservoir computing, you need to understand a bit about how\u00a0<a href=\"https:\/\/spectrum.ieee.org\/computing\/software\/the-neural-network-that-remembers\">artificial neural networks<\/a>(ANNs) operate. These ANNs take data on board through an input layer,\u00a0transform that data in a hidden layer of computational units often called neurons, and then give the final interpretation of that data in an output layer. Reservoir computing is most often used on inputs that depend on time (as opposed to inputs such as images, which are static).<\/p>\n<p>So reservoir computing uses a dynamical system driven by the time-dependent input. The dynamical system is chosen to be relatively complex, so its response to the input can be fairly different from the input itself.<\/p>\n<p>Also, the system is chosen to have multiple degrees of freedom for responding to the input. As a result, the input is \u201cmapped\u201d\u00a0to a trajectory in a high-dimensional space, each dimension corresponding to one of the degrees of freedom. This creates a lot of information \u201crichness,\u201d meaning that there have been many different transformations of the input.<\/p>\n<p>\u201cThe special trick used by reservoir computing is to combine all the dimensions linearly to get an output that corresponds to what we want the computer to give as an answer for a given input,\u201d said Sylvestre. \u201cThat\u2019s what we call \u2018training\u2019\u00a0the reservoir computing. The linear combination is very simple to compute, unlike other approaches to AI, where one would attempt to modify the inner working of the dynamical system to get the desired output.\u201d<\/p>\n<p>In most reservoir computing systems, the dynamical system is the software. In this work, the dynamical system is the MEMS device itself. To achieve this dynamical system, the device uses the nonlinear dynamics of how a very thin silicon beam oscillates in space. These oscillations create a kind of neural network that transforms the input signal into the higher dimensional space required for neural network computing.<\/p>\n<p>Sylvestre explained that it\u2019s hard to modify the inner workings of a MEMS device, but it\u2019s not necessary in reservoir computing, which is why they used this approach to do AI in MEMS.<\/p>\n<p>\u201cOur work shows that it\u2019s possible to use the nonlinear resources in MEMS to do AI,\u201d said Sylvestre. \u201cIt\u2019s a novel way to build \u2018artificially smart\u2019\u00a0devices that can be really small and efficient.\u201d<\/p>\n<p>It\u2019s difficult to compare the processing power of this MEMS device with a known quantity, like a desktop computer, according to Sylvestre. \u201cThe computer and our MEMS work very differently,\u201d he explained. \u201cWhile a computer is big and consumes lots of power (tens of watts), our MEMS could fit on the tip of a human hair, and runs on microwatts of power. Still, they can do fancy tricks, like classifying spoken words\u2014a task that would probably use 10 percent [of the resources] of a desktop computer.\u201d<\/p>\n<p>A possible application for this AI-equipped MEMS could be an accelerometer MEMS in which all the data the device is collecting is processed within the device without the need for sending that data back to a computer, according to Sylvestre.<\/p>\n<p>While the researchers have not yet focused on how they would power these MEMS, it\u2019s assumed that the devices\u2019 miserly power use would allow them to run\u00a0on\u00a0only\u00a0energy harvesters without the need for batteries. With that in mind, the researchers are looking to apply their AI MEMS approach to applications in sensing and robot control.<\/p>\n<p>Featured Image: Guillaume DionA single silicon beam (red), along with its drive (yellow) and readout (green and blue) electrodes, implements a MEMS capable of nontrivial computations.<\/p>\n","protected":false},"excerpt":{"rendered":"<p>For the first time, artificial intelligence has been integrated into a MEMS device<\/p>\n","protected":false},"author":1,"featured_media":5809,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"_monsterinsights_skip_tracking":false,"_monsterinsights_sitenote_active":false,"_monsterinsights_sitenote_note":"","_monsterinsights_sitenote_category":0,"amp_status":"","_jetpack_memberships_contains_paid_content":false,"footnotes":"","jetpack_publicize_message":"AI on a MEMS Device Brings Neuromorphic Computing to the Edge","jetpack_publicize_feature_enabled":true,"jetpack_social_post_already_shared":true,"jetpack_social_options":{"image_generator_settings":{"template":"highway","enabled":false}}},"categories":[208,242,5],"tags":[],"jetpack_publicize_connections":[],"yoast_head":"<!-- This site is optimized with the Yoast SEO plugin v22.8 - https:\/\/yoast.com\/wordpress\/plugins\/seo\/ -->\n<title>AI on a MEMS Device Brings Neuromorphic Computing to the Edge - AthisNews<\/title>\n<meta name=\"robots\" content=\"index, follow, max-snippet:-1, max-image-preview:large, max-video-preview:-1\" \/>\n<link rel=\"canonical\" href=\"https:\/\/athis-technologies.com\/news\/innovation\/manufacturing\/2018\/ai-on-a-mems-device-brings-neuromorphic-computing-to-the-edge\/\" \/>\n<meta property=\"og:locale\" content=\"en_US\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"AI on a MEMS Device Brings Neuromorphic Computing to the Edge - AthisNews\" \/>\n<meta property=\"og:description\" content=\"For the first time, artificial intelligence has been integrated into a MEMS device\" \/>\n<meta property=\"og:url\" content=\"https:\/\/athis-technologies.com\/news\/innovation\/manufacturing\/2018\/ai-on-a-mems-device-brings-neuromorphic-computing-to-the-edge\/\" \/>\n<meta property=\"og:site_name\" content=\"AthisNews\" \/>\n<meta property=\"article:publisher\" content=\"https:\/\/www.facebook.com\/AthisNews-271175647014395\/\" \/>\n<meta property=\"article:author\" content=\"https:\/\/www.facebook.com\/AthisNews-271175647014395\/\" \/>\n<meta property=\"article:published_time\" content=\"2018-10-18T06:59:59+00:00\" \/>\n<meta property=\"article:modified_time\" content=\"2018-10-18T07:08:13+00:00\" \/>\n<meta property=\"og:image\" content=\"https:\/\/athis-technologies.com\/news\/wp-content\/uploads\/2018\/10\/MzE1MTgwOA.jpeg\" \/>\n\t<meta property=\"og:image:width\" content=\"1240\" \/>\n\t<meta property=\"og:image:height\" content=\"930\" \/>\n\t<meta property=\"og:image:type\" content=\"image\/jpeg\" \/>\n<meta name=\"author\" content=\"Ashley Reyes\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:creator\" content=\"@https:\/\/twitter.com\/AshleyReyesCom\" \/>\n<meta name=\"twitter:site\" content=\"@Athis_News\" \/>\n<meta name=\"twitter:label1\" content=\"Written by\" \/>\n\t<meta name=\"twitter:data1\" content=\"Dexter Johnson\" \/>\n\t<meta name=\"twitter:label2\" content=\"Est. reading time\" \/>\n\t<meta name=\"twitter:data2\" content=\"4 minutes\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\/\/schema.org\",\"@graph\":[{\"@type\":\"WebPage\",\"@id\":\"https:\/\/athis-technologies.com\/news\/innovation\/manufacturing\/2018\/ai-on-a-mems-device-brings-neuromorphic-computing-to-the-edge\/\",\"url\":\"https:\/\/athis-technologies.com\/news\/innovation\/manufacturing\/2018\/ai-on-a-mems-device-brings-neuromorphic-computing-to-the-edge\/\",\"name\":\"AI on a MEMS Device Brings Neuromorphic Computing to the Edge - AthisNews\",\"isPartOf\":{\"@id\":\"https:\/\/athis-technologies.com\/news\/#website\"},\"primaryImageOfPage\":{\"@id\":\"https:\/\/athis-technologies.com\/news\/innovation\/manufacturing\/2018\/ai-on-a-mems-device-brings-neuromorphic-computing-to-the-edge\/#primaryimage\"},\"image\":{\"@id\":\"https:\/\/athis-technologies.com\/news\/innovation\/manufacturing\/2018\/ai-on-a-mems-device-brings-neuromorphic-computing-to-the-edge\/#primaryimage\"},\"thumbnailUrl\":\"https:\/\/athis-technologies.com\/news\/wp-content\/uploads\/2018\/10\/MzE1MTgwOA.jpeg\",\"datePublished\":\"2018-10-18T06:59:59+00:00\",\"dateModified\":\"2018-10-18T07:08:13+00:00\",\"author\":{\"@id\":\"https:\/\/athis-technologies.com\/news\/#\/schema\/person\/77a4a54746e7c6eece2474c96338c6d0\"},\"breadcrumb\":{\"@id\":\"https:\/\/athis-technologies.com\/news\/innovation\/manufacturing\/2018\/ai-on-a-mems-device-brings-neuromorphic-computing-to-the-edge\/#breadcrumb\"},\"inLanguage\":\"en-US\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\/\/athis-technologies.com\/news\/innovation\/manufacturing\/2018\/ai-on-a-mems-device-brings-neuromorphic-computing-to-the-edge\/\"]}]},{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\/\/athis-technologies.com\/news\/innovation\/manufacturing\/2018\/ai-on-a-mems-device-brings-neuromorphic-computing-to-the-edge\/#primaryimage\",\"url\":\"https:\/\/athis-technologies.com\/news\/wp-content\/uploads\/2018\/10\/MzE1MTgwOA.jpeg\",\"contentUrl\":\"https:\/\/athis-technologies.com\/news\/wp-content\/uploads\/2018\/10\/MzE1MTgwOA.jpeg\",\"width\":1240,\"height\":930},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\/\/athis-technologies.com\/news\/innovation\/manufacturing\/2018\/ai-on-a-mems-device-brings-neuromorphic-computing-to-the-edge\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Home\",\"item\":\"https:\/\/athis-technologies.com\/news\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"AI on a MEMS Device Brings Neuromorphic Computing to the Edge\"}]},{\"@type\":\"WebSite\",\"@id\":\"https:\/\/athis-technologies.com\/news\/#website\",\"url\":\"https:\/\/athis-technologies.com\/news\/\",\"name\":\"AthisNews\",\"description\":\"More than Words\",\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\/\/athis-technologies.com\/news\/?s={search_term_string}\"},\"query-input\":\"required name=search_term_string\"}],\"inLanguage\":\"en-US\"},{\"@type\":\"Person\",\"@id\":\"https:\/\/athis-technologies.com\/news\/#\/schema\/person\/77a4a54746e7c6eece2474c96338c6d0\",\"name\":\"Ashley Reyes\",\"image\":{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\/\/athis-technologies.com\/news\/#\/schema\/person\/image\/\",\"url\":\"https:\/\/athis-technologies.com\/news\/wp-content\/uploads\/2018\/08\/cFdsqpqq-100x100.jpg\",\"contentUrl\":\"https:\/\/athis-technologies.com\/news\/wp-content\/uploads\/2018\/08\/cFdsqpqq-100x100.jpg\",\"caption\":\"Ashley Reyes\"},\"description\":\"Social Media Development addict, Ashley Reyes is specialised on Emerging Techs &amp; Crowdfunding Market. Ashley holds a Bachelor in Marketing and have 5+ years of experience in leader company as Marketing Intelligence Analyst . She is now Chief Community Officer at Athis News.\",\"sameAs\":[\"https:\/\/athis-technologies.com\/news\/?author=1\",\"https:\/\/www.facebook.com\/AthisNews-271175647014395\/\",\"https:\/\/www.linkedin.com\/in\/ashley-reyes\/\",\"https:\/\/x.com\/https:\/\/twitter.com\/AshleyReyesCom\"],\"url\":\"#molongui-disabled-link\"}]}<\/script>\n<!-- \/ Yoast SEO plugin. -->","yoast_head_json":{"title":"AI on a MEMS Device Brings Neuromorphic Computing to the Edge - AthisNews","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:\/\/athis-technologies.com\/news\/innovation\/manufacturing\/2018\/ai-on-a-mems-device-brings-neuromorphic-computing-to-the-edge\/","og_locale":"en_US","og_type":"article","og_title":"AI on a MEMS Device Brings Neuromorphic Computing to the Edge - AthisNews","og_description":"For the first time, artificial intelligence has been integrated into a MEMS device","og_url":"https:\/\/athis-technologies.com\/news\/innovation\/manufacturing\/2018\/ai-on-a-mems-device-brings-neuromorphic-computing-to-the-edge\/","og_site_name":"AthisNews","article_publisher":"https:\/\/www.facebook.com\/AthisNews-271175647014395\/","article_author":"https:\/\/www.facebook.com\/AthisNews-271175647014395\/","article_published_time":"2018-10-18T06:59:59+00:00","article_modified_time":"2018-10-18T07:08:13+00:00","og_image":[{"width":1240,"height":930,"url":"https:\/\/athis-technologies.com\/news\/wp-content\/uploads\/2018\/10\/MzE1MTgwOA.jpeg","type":"image\/jpeg"}],"author":"Ashley Reyes","twitter_card":"summary_large_image","twitter_creator":"@https:\/\/twitter.com\/AshleyReyesCom","twitter_site":"@Athis_News","twitter_misc":{"Written by":"Dexter Johnson","Est. reading time":"4 minutes"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"WebPage","@id":"https:\/\/athis-technologies.com\/news\/innovation\/manufacturing\/2018\/ai-on-a-mems-device-brings-neuromorphic-computing-to-the-edge\/","url":"https:\/\/athis-technologies.com\/news\/innovation\/manufacturing\/2018\/ai-on-a-mems-device-brings-neuromorphic-computing-to-the-edge\/","name":"AI on a MEMS Device Brings Neuromorphic Computing to the Edge - AthisNews","isPartOf":{"@id":"https:\/\/athis-technologies.com\/news\/#website"},"primaryImageOfPage":{"@id":"https:\/\/athis-technologies.com\/news\/innovation\/manufacturing\/2018\/ai-on-a-mems-device-brings-neuromorphic-computing-to-the-edge\/#primaryimage"},"image":{"@id":"https:\/\/athis-technologies.com\/news\/innovation\/manufacturing\/2018\/ai-on-a-mems-device-brings-neuromorphic-computing-to-the-edge\/#primaryimage"},"thumbnailUrl":"https:\/\/athis-technologies.com\/news\/wp-content\/uploads\/2018\/10\/MzE1MTgwOA.jpeg","datePublished":"2018-10-18T06:59:59+00:00","dateModified":"2018-10-18T07:08:13+00:00","author":{"@id":"https:\/\/athis-technologies.com\/news\/#\/schema\/person\/77a4a54746e7c6eece2474c96338c6d0"},"breadcrumb":{"@id":"https:\/\/athis-technologies.com\/news\/innovation\/manufacturing\/2018\/ai-on-a-mems-device-brings-neuromorphic-computing-to-the-edge\/#breadcrumb"},"inLanguage":"en-US","potentialAction":[{"@type":"ReadAction","target":["https:\/\/athis-technologies.com\/news\/innovation\/manufacturing\/2018\/ai-on-a-mems-device-brings-neuromorphic-computing-to-the-edge\/"]}]},{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/athis-technologies.com\/news\/innovation\/manufacturing\/2018\/ai-on-a-mems-device-brings-neuromorphic-computing-to-the-edge\/#primaryimage","url":"https:\/\/athis-technologies.com\/news\/wp-content\/uploads\/2018\/10\/MzE1MTgwOA.jpeg","contentUrl":"https:\/\/athis-technologies.com\/news\/wp-content\/uploads\/2018\/10\/MzE1MTgwOA.jpeg","width":1240,"height":930},{"@type":"BreadcrumbList","@id":"https:\/\/athis-technologies.com\/news\/innovation\/manufacturing\/2018\/ai-on-a-mems-device-brings-neuromorphic-computing-to-the-edge\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https:\/\/athis-technologies.com\/news\/"},{"@type":"ListItem","position":2,"name":"AI on a MEMS Device Brings Neuromorphic Computing to the Edge"}]},{"@type":"WebSite","@id":"https:\/\/athis-technologies.com\/news\/#website","url":"https:\/\/athis-technologies.com\/news\/","name":"AthisNews","description":"More than Words","potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/athis-technologies.com\/news\/?s={search_term_string}"},"query-input":"required name=search_term_string"}],"inLanguage":"en-US"},{"@type":"Person","@id":"https:\/\/athis-technologies.com\/news\/#\/schema\/person\/77a4a54746e7c6eece2474c96338c6d0","name":"Ashley Reyes","image":{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/athis-technologies.com\/news\/#\/schema\/person\/image\/","url":"https:\/\/athis-technologies.com\/news\/wp-content\/uploads\/2018\/08\/cFdsqpqq-100x100.jpg","contentUrl":"https:\/\/athis-technologies.com\/news\/wp-content\/uploads\/2018\/08\/cFdsqpqq-100x100.jpg","caption":"Ashley Reyes"},"description":"Social Media Development addict, Ashley Reyes is specialised on Emerging Techs &amp; Crowdfunding Market. Ashley holds a Bachelor in Marketing and have 5+ years of experience in leader company as Marketing Intelligence Analyst . She is now Chief Community Officer at Athis News.","sameAs":["https:\/\/athis-technologies.com\/news\/?author=1","https:\/\/www.facebook.com\/AthisNews-271175647014395\/","https:\/\/www.linkedin.com\/in\/ashley-reyes\/","https:\/\/x.com\/https:\/\/twitter.com\/AshleyReyesCom"],"url":"#molongui-disabled-link"}]}},"jetpack_sharing_enabled":true,"jetpack_featured_media_url":"https:\/\/athis-technologies.com\/news\/wp-content\/uploads\/2018\/10\/MzE1MTgwOA.jpeg","jetpack_shortlink":"https:\/\/wp.me\/p9Volu-1vG","_links":{"self":[{"href":"https:\/\/athis-technologies.com\/news\/wp-json\/wp\/v2\/posts\/5808"}],"collection":[{"href":"https:\/\/athis-technologies.com\/news\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/athis-technologies.com\/news\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/athis-technologies.com\/news\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/athis-technologies.com\/news\/wp-json\/wp\/v2\/comments?post=5808"}],"version-history":[{"count":0,"href":"https:\/\/athis-technologies.com\/news\/wp-json\/wp\/v2\/posts\/5808\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/athis-technologies.com\/news\/wp-json\/wp\/v2\/media\/5809"}],"wp:attachment":[{"href":"https:\/\/athis-technologies.com\/news\/wp-json\/wp\/v2\/media?parent=5808"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/athis-technologies.com\/news\/wp-json\/wp\/v2\/categories?post=5808"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/athis-technologies.com\/news\/wp-json\/wp\/v2\/tags?post=5808"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}