{"id":489302,"date":"2022-08-31T23:30:32","date_gmt":"2022-08-31T20:30:32","guid":{"rendered":"https:\/\/en.buradabiliyorum.com\/new-neuromorphic-approach-could-make-future-robots-smarter\/"},"modified":"2022-08-31T23:30:32","modified_gmt":"2022-08-31T20:30:32","slug":"new-neuromorphic-approach-could-make-future-robots-smarter","status":"publish","type":"post","link":"https:\/\/buradabiliyorum.com\/en\/new-neuromorphic-approach-could-make-future-robots-smarter\/","title":{"rendered":"#New neuromorphic approach could make future robots smarter"},"content":{"rendered":"<div id=\"ez-toc-container\" class=\"ez-toc-v2_0_84 counter-hierarchy ez-toc-counter ez-toc-custom ez-toc-container-direction\">\n<p class=\"ez-toc-title\" style=\"cursor:inherit\">Table of Contents<\/p>\n<label for=\"ez-toc-cssicon-toggle-item-6a2738f92f5c7\" class=\"ez-toc-cssicon-toggle-label\"><span class=\"\"><span class=\"eztoc-hide\" style=\"display:none;\">Toggle<\/span><span class=\"ez-toc-icon-toggle-span\"><svg style=\"fill: #dd3333;color:#dd3333\" xmlns=\"http:\/\/www.w3.org\/2000\/svg\" class=\"list-377408\" width=\"20px\" height=\"20px\" viewBox=\"0 0 24 24\" fill=\"none\"><path d=\"M6 6H4v2h2V6zm14 0H8v2h12V6zM4 11h2v2H4v-2zm16 0H8v2h12v-2zM4 16h2v2H4v-2zm16 0H8v2h12v-2z\" fill=\"currentColor\"><\/path><\/svg><svg style=\"fill: #dd3333;color:#dd3333\" class=\"arrow-unsorted-368013\" xmlns=\"http:\/\/www.w3.org\/2000\/svg\" width=\"10px\" height=\"10px\" viewBox=\"0 0 24 24\" version=\"1.2\" baseProfile=\"tiny\"><path d=\"M18.2 9.3l-6.2-6.3-6.2 6.3c-.2.2-.3.4-.3.7s.1.5.3.7c.2.2.4.3.7.3h11c.3 0 .5-.1.7-.3.2-.2.3-.5.3-.7s-.1-.5-.3-.7zM5.8 14.7l6.2 6.3 6.2-6.3c.2-.2.3-.5.3-.7s-.1-.5-.3-.7c-.2-.2-.4-.3-.7-.3h-11c-.3 0-.5.1-.7.3-.2.2-.3.5-.3.7s.1.5.3.7z\"\/><\/svg><\/span><\/span><\/label><input type=\"checkbox\"  id=\"ez-toc-cssicon-toggle-item-6a2738f92f5c7\" checked aria-label=\"Toggle\" \/><nav><ul class='ez-toc-list ez-toc-list-level-1 ' ><li class='ez-toc-page-1 ez-toc-heading-level-1'><a class=\"ez-toc-link ez-toc-heading-1\" href=\"https:\/\/buradabiliyorum.com\/en\/new-neuromorphic-approach-could-make-future-robots-smarter\/#%E2%80%9CNew_neuromorphic_approach_could_make_future_robots_smarter%E2%80%9D\" >&#8220;New neuromorphic approach could make future robots smarter&#8221;<\/a><ul class='ez-toc-list-level-2' ><li class='ez-toc-heading-level-2'><a class=\"ez-toc-link ez-toc-heading-2\" href=\"https:\/\/buradabiliyorum.com\/en\/new-neuromorphic-approach-could-make-future-robots-smarter\/#Greetings_humanoids\" >Greetings, humanoids<\/a><\/li><li class='ez-toc-page-1 ez-toc-heading-level-2'><a class=\"ez-toc-link ez-toc-heading-3\" href=\"https:\/\/buradabiliyorum.com\/en\/new-neuromorphic-approach-could-make-future-robots-smarter\/#Interactive_learning\" >Interactive learning<\/a><\/li><li class='ez-toc-page-1 ez-toc-heading-level-2'><a class=\"ez-toc-link ez-toc-heading-4\" href=\"https:\/\/buradabiliyorum.com\/en\/new-neuromorphic-approach-could-make-future-robots-smarter\/#Neuromorphic_simulations\" >Neuromorphic simulations<\/a><\/li><\/ul><\/li><\/ul><\/nav><\/div>\n<h1><span class=\"ez-toc-section\" id=\"%E2%80%9CNew_neuromorphic_approach_could_make_future_robots_smarter%E2%80%9D\"><\/span>&#8220;New neuromorphic approach could make future robots smarter&#8221;<span class=\"ez-toc-section-end\"><\/span><\/h1>\n<div id=\"article-main-content\">\n                            Scientists have t<a href=\"https:\/\/buradabiliyorum.com\/en\/category\/download-scripts-themes-apps\/\" data-internallinksmanager029f6b8e52c=\"9\" title=\"Download Scripts &amp; Themes &amp; Apps\" target=\"_blank\" rel=\"noopener\">app<\/a>ed neuromorphic computing to keep <span>robots\u00a0learning\u00a0about new objects after they\u2019ve been deployed.<\/span><\/p>\n<p>For the uninitiated, neuromorphic computing replicates the neural structure of the human brain to create algorithms that can deal with the uncertainties of the natural world.<\/p>\n<p>Intel Labs has developed one of the most notable architectures in the field: the <a rel=\"nofollow noopener\" target=\"_blank\" href=\"https:\/\/www.intel.com\/content\/www\/us\/en\/research\/neuromorphic-computing.html\">Loihi<\/a><span> neuromorphic chip.<\/span><\/p>\n<div class=\"inarticle-wrapper neural channel-cta hs-embed-tnw\">\n<div id=\"hs-embed-tnw\" class=\"channel-cta-wrapper\">\n<div class=\"channel-cta-img\"><img class=\"js-lazy\" https:=\"\"\/><\/div>\n<p><noscript><img decoding=\"async\" src=\"https:\/\/thenextweb.com\/news\/src=\" https:=\"\"\/><\/noscript><\/p>\n<div class=\"channel-cta-input\">\n<h2 class=\"channel-cta-title\"><span class=\"ez-toc-section\" id=\"Greetings_humanoids\"><\/span>Greetings, humanoids<span class=\"ez-toc-section-end\"><\/span><\/h2>\n<p class=\"channel-cta-tagline\">Subscribe to our <a href=\"https:\/\/buradabiliyorum.com\/en\/category\/news\/\" data-internallinksmanager029f6b8e52c=\"2\" title=\"News\" target=\"_blank\" rel=\"noopener\">news<\/a>letter now for a weekly recap of our favorite AI stories in your inbox.<\/p>\n<\/div>\n<\/div>\n<\/div>\n<p>Loihi is comprised of around 130,000 artificial neurons, which send information to each other across a \u201cspiking\u201d neural network (SNN). The chips had already powered a range of systems<span>, from an smart artificial skin to an electronic \u201cnose\u201d that recognizes scents emitted from explosives.<\/span><\/p>\n<p>Intel Labs this week unveiled another application. The research unit teamed up<span> with the Italian Institute of <a href=\"https:\/\/buradabiliyorum.com\/en\/category\/technology\/\" data-internallinksmanager029f6b8e52c=\"4\" title=\"Technology\" target=\"_blank\" rel=\"noopener\">Technology<\/a> and the Technical University of Munich to deploy Loihi in a new approach to continual learning for robotics.<\/span><\/p>\n<h2><span class=\"ez-toc-section\" id=\"Interactive_learning\"><\/span>Interactive learning<span class=\"ez-toc-section-end\"><\/span><\/h2>\n<p>The method targets systems that interact with unconstrained environments, such as future robotic assistants for healthcare and manufacturing.<\/p>\n<p>Existing deep neural networks can struggle with object learning in these scenarios, as they require extensive well-prepared training data \u2014\u00a0and careful retraining on new objects they encounter. The new neuromorphic approach aims to overcomes these limitations.<\/p>\n<p>The researchers first implemented an SNN on Loihi. This architecture <span>localizes learning to a single layer of plastic synapses. It also accounts for different views of objects by adding new neurons on demand. <\/span><\/p>\n<p><span>As a result, the learning process unfolds autonomously while interacting with the user.<\/span><\/p>\n<h2><span class=\"ez-toc-section\" id=\"Neuromorphic_simulations\"><\/span>Neuromorphic simulations<span class=\"ez-toc-section-end\"><\/span><\/h2>\n<p>The team tested their approach in a simulated 3D environment. In this setup, the<span>\u00a0robot actively senses objects by moving an event-based camera that functions as its eyes. <\/span><\/p>\n<p><span>The camera\u2019s sensor \u201csees\u201d objects in a manner inspired by small fixational eye movements called \u201cmicrosaccades.\u201d\u00a0 If the object it views is new, the SNN representation is learned or updated. If the object\u00a0 is known, the network recognizes it and provides feedback to the user.<\/span><\/p>\n<figure class=\"post-image post-mediaBleed aligncenter\"><img loading=\"lazy\" class=\"size-full wp-image-1391128 js-lazy\" alt=\"In a simulated setup, the robot actively senses objects by moving its eyes (event-based camera, or Dynamic Vision Sensor), generating \u201cmiscrosaccades\u201d. The events collected are used to drive a spiking neural network (SNN) on the Loihi chip. If the object or the view is new, its SNN representation is learned or updated. If the object is known, it is recognized by the network and respective feedback is given to the user.\" width=\"1669\" height=\"902\" sizes=\"auto, (max-width: 1669px) 100vw, 1669px\" https:=\"\" srcset=\"https:\/\/cdn0.tnwcdn.com\/wp-content\/blogs.dir\/1\/files\/2022\/08\/Still-image_robot-1.jpg 1669w, https:\/\/cdn0.tnwcdn.com\/wp-content\/blogs.dir\/1\/files\/2022\/08\/Still-image_robot-1-280x151.jpg 280w, https:\/\/cdn0.tnwcdn.com\/wp-content\/blogs.dir\/1\/files\/2022\/08\/Still-image_robot-1-250x135.jpg 250w, https:\/\/cdn0.tnwcdn.com\/wp-content\/blogs.dir\/1\/files\/2022\/08\/Still-image_robot-1-500x270.jpg 500w, https:\/\/cdn0.tnwcdn.com\/wp-content\/blogs.dir\/1\/files\/2022\/08\/Still-image_robot-1-1536x830.jpg 1536w, https:\/\/cdn0.tnwcdn.com\/wp-content\/blogs.dir\/1\/files\/2022\/08\/Still-image_robot-1-796x430.jpg 796w, https:\/\/cdn0.tnwcdn.com\/wp-content\/blogs.dir\/1\/files\/2022\/08\/Still-image_robot-1-1592x860.jpg 1592w\"\/><figcaption><a rel=\"nofollow noopener\" target=\"_blank\" href=\"#\" data-url=\"https:\/\/twitter.com\/intent\/tweet?url=https%3A%2F%2Feditorial.thenextweb.com%2Fneural%2F2022%2F08%2F31%2Fintel-unveils-neuromorphic-approach-to-interactive-continual-learning-robots%2F&amp;via=thenextweb&amp;related=thenextweb&amp;text=Check out this picture on: The data collected by the camera drives an SNN on the Loihi chip. Credit: Intel Labs\" data-title=\"Share The data collected by the camera drives an SNN on the Loihi chip. Credit: Intel Labs on Twitter\" data-width=\"685\" data-height=\"500\" class=\"post-image-share popitup\" title=\"Share The data collected by the camera drives an SNN on the Loihi chip. Credit: Intel Labs on Twitter\"><i class=\"icon icon--inline icon--twitter--dark\"\/><\/a>The data collected by the camera drives an SNN on the Loihi chip. Credit: Intel Labs<\/figcaption><noscript><img loading=\"lazy\" class=\"size-full wp-image-1391128\" https:=\"\" alt=\"In a simulated setup, the robot actively senses objects by moving its eyes (event-based camera, or Dynamic Vision Sensor), generating \u201cmiscrosaccades\u201d. The events collected are used to drive a spiking neural network (SNN) on the Loihi chip. If the object or the view is new, its SNN representation is learned or updated. If the object is known, it is recognized by the network and respective feedback is given to the user.\" width=\"1669\" height=\"902\" srcset=\"https:\/\/cdn0.tnwcdn.com\/wp-content\/blogs.dir\/1\/files\/2022\/08\/Still-image_robot-1.jpg 1669w, https:\/\/cdn0.tnwcdn.com\/wp-content\/blogs.dir\/1\/files\/2022\/08\/Still-image_robot-1-280x151.jpg 280w, https:\/\/cdn0.tnwcdn.com\/wp-content\/blogs.dir\/1\/files\/2022\/08\/Still-image_robot-1-250x135.jpg 250w, https:\/\/cdn0.tnwcdn.com\/wp-content\/blogs.dir\/1\/files\/2022\/08\/Still-image_robot-1-500x270.jpg 500w, https:\/\/cdn0.tnwcdn.com\/wp-content\/blogs.dir\/1\/files\/2022\/08\/Still-image_robot-1-1536x830.jpg 1536w, https:\/\/cdn0.tnwcdn.com\/wp-content\/blogs.dir\/1\/files\/2022\/08\/Still-image_robot-1-796x430.jpg 796w, https:\/\/cdn0.tnwcdn.com\/wp-content\/blogs.dir\/1\/files\/2022\/08\/Still-image_robot-1-1592x860.jpg 1592w\"\/><\/noscript><\/figure>\n<p>The team say their method required up to 175-times lower energy to provide similar or better speed and accuracy than conventional methods running on a CPU.<\/p>\n<p>They now need to test their algorithm in the real-world with actual robots.<\/p>\n<p><span>\u201cOur goal is to apply similar capabilities to future robots that work in interactive settings, enabling them to adapt to the unforeseen and work more naturally alongside humans,\u201d Yulia Sandamirskaya, the study\u2019s senior author, said in a statement.\u00a0<\/span><\/p>\n<p>Their study, which was<span class=\"m_-6901499767236946286normaltextrun\"><span>\u00a0named \u201cBest Paper\u201d at this year\u2019s International Conference on Neuromorphic Systems (ICONS), can be read <a rel=\"nofollow noopener\" target=\"_blank\" href=\"http:\/\/sandamirskaya.eu\/resources\/Interactive_Continual_Learning_for_Robots__Neuromorphic_Approach__ICONS_.pdf\">here<\/a>.<\/span><\/span>\n                        <\/div>\n<p><script async src=\"\/\/platform.twitter.com\/widgets.js\" charset=\"utf-8\"><\/script><\/p>\n<blockquote><p><strong><span style=\"color: #ff6600;\">If you liked the article, do not forget to share it with your friends. Follow us on\u00a0<span style=\"color: #ff0000;\"><a style=\"color: #ff0000;\" href=\"https:\/\/news.google.com\/publications\/CAAqBwgKMLG0nwswvr63Aw\" target=\"_blank\" rel=\"nofollow noopener noreferrer\">Google News<\/a><\/span>\u00a0too, click on the star and choose us from your favorites.<\/span><\/strong><\/p><\/blockquote>\n<blockquote>\n<p style=\"text-align: center;\">For forums sites go to <span style=\"color: #ff9900;\"><a style=\"color: #ff9900;\" href=\"https:\/\/forum.buradabiliyorum.com\/\" target=\"_blank\" rel=\"noopener\">Forum.BuradaBiliyorum.Com<\/a><\/span><\/strong><\/p>\n<\/blockquote>\n<blockquote>\n<p style=\"text-align: center;\"><strong>If you want to read more like this article, you can visit our <span style=\"color: #ff9900;\"><a style=\"color: #ff9900;\" href=\"https:\/\/en.buradabiliyorum.com\/technology\/\" target=\"_blank\" rel=\"noopener\">Technology category.<\/a><\/span><\/strong><\/p>\n<\/blockquote>\n<p><span style=\"color: black;\"><a style=\"color: #ff9900;\" href=\"https:\/\/thenextweb.com\/news\/intel-unveils-neuromorphic-approach-to-interactive-continual-learning-robots\" target=\"_blank\" rel=\"noopener\">Source<\/a><\/span><\/p>\n","protected":false},"excerpt":{"rendered":"<p>&#8220;New neuromorphic approach could make future robots smarter&#8221; Scientists have tapped neuromorphic computing to keep robots\u00a0learning\u00a0about new objects after they\u2019ve been deployed. For the uninitiated, neuromorphic computing replicates the neural structure of the human brain to create algorithms that can deal with the uncertainties of the natural world. Intel Labs has developed one of the&#8230;<\/p>\n","protected":false},"author":1,"featured_media":489303,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"fifu_image_url":"https:\/\/img-cdn.tnwcdn.com\/image\/neural?filter_last=1&fit=1280,640&url=https:\/\/cdn0.tnwcdn.com\/wp-content\/blogs.dir\/1\/files\/2022\/08\/Untitled-design-6.jpg&signature=fe6a94dfb5f82c93a55c56fd9ef7f50c","fifu_image_alt":"","footnotes":""},"categories":[18],"tags":[],"class_list":["post-489302","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-technology"],"_links":{"self":[{"href":"https:\/\/buradabiliyorum.com\/en\/wp-json\/wp\/v2\/posts\/489302","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/buradabiliyorum.com\/en\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/buradabiliyorum.com\/en\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/buradabiliyorum.com\/en\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/buradabiliyorum.com\/en\/wp-json\/wp\/v2\/comments?post=489302"}],"version-history":[{"count":0,"href":"https:\/\/buradabiliyorum.com\/en\/wp-json\/wp\/v2\/posts\/489302\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/buradabiliyorum.com\/en\/wp-json\/wp\/v2\/media\/489303"}],"wp:attachment":[{"href":"https:\/\/buradabiliyorum.com\/en\/wp-json\/wp\/v2\/media?parent=489302"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/buradabiliyorum.com\/en\/wp-json\/wp\/v2\/categories?post=489302"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/buradabiliyorum.com\/en\/wp-json\/wp\/v2\/tags?post=489302"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}