{"id":8879,"date":"2022-09-13T17:31:53","date_gmt":"2022-09-13T16:31:53","guid":{"rendered":"https:\/\/telecomkh.info\/?p=8879"},"modified":"2022-09-13T17:31:53","modified_gmt":"2022-09-13T16:31:53","slug":"intel-labs-improves-interactive-continual-learning-for-robots%e2%80%afwith-neuromorphic-computing","status":"publish","type":"post","link":"https:\/\/telecomkh.info\/?p=8879","title":{"rendered":"Intel Labs improves interactive, continual learning for robots\u202fwith neuromorphic computing"},"content":{"rendered":"<p><strong>Neuromorphic research chip Loihi demonstrates real-time learning with 175x lower energy<\/strong><\/p>\n<p>Intel Labs, in collaboration with the Italian Institute of Technology and the Technical University of Munich, has introduced a new approach to neural network-based object learning. It specifically targets future applications like robotic assistants that interact with unconstrained environments, including in logistics, healthcare or elderly care. This research is a crucial step in improving the capabilities of future assistive or manufacturing robots. It uses neuromorphic computing through new interactive online object learning methods to enable robots to learn new objects after deployment.<br \/>\nUsing these new models, Intel and its collaborators successfully demonstrated continual interactive learning on Intel\u2019s neuromorphic research chip, Loihi, measuring up to 175x lower energy to learn a new object instance with similar or better speed and accuracy compared to conventional methods running on a central processing unit (CPU). To accomplish this, researchers implemented a spiking neural network architecture on Loihi that localized learning to a single layer of plastic synapses and accounted for different object views by recruiting new neurons on demand. This enabled the learning process to unfold autonomously while interacting with the user.<br \/>\nThe research was published in the paper \u201cInteractive continual learning for robots: a neuromorphic approach,\u201d which was named \u201cBest Paper\u201d at this year\u2019s International Conference on Neuromorphic Systems (ICONS) hosted by Oak Ridge National Laboratory.<br \/>\n\u201cWhen a human learns a new object, they take a look, turn it around, ask what it is, and then they\u2019re able to recognize it again in all kinds of settings and conditions instantaneously,\u201d said Yulia Sandamirskaya, robotics research lead in Intel\u2019s neuromorphic computing lab and senior author of the paper. \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. Our results with Loihi reinforce the value of neuromorphic computing for the future of robotics.\u201d<\/p>\n<p><span style=\"color: #999999;\"><em>Above, image credited to Intel<\/em><\/span><\/p>\n","protected":false},"excerpt":{"rendered":"<p>Neuromorphic research chip Loihi demonstrates real-time learning with 175x lower energy Intel Labs, in collaboration with the Italian Institute of Technology and the Technical University of Munich, has introduced a new approach to neural network-based object learning. It specifically targets future applications like robotic assistants that interact with unconstrained environments, including in logistics, healthcare or &hellip; <\/p>\n<p class=\"link-more\"><a href=\"https:\/\/telecomkh.info\/?p=8879\" class=\"more-link\">Continue reading<span class=\"screen-reader-text\"> \u00abIntel Labs improves interactive, continual learning for robots\u202fwith neuromorphic computing\u00bb<\/span><\/a><\/p>\n","protected":false},"author":1,"featured_media":8880,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":[],"categories":[61],"tags":[],"_links":{"self":[{"href":"https:\/\/telecomkh.info\/index.php?rest_route=\/wp\/v2\/posts\/8879"}],"collection":[{"href":"https:\/\/telecomkh.info\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/telecomkh.info\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/telecomkh.info\/index.php?rest_route=\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/telecomkh.info\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=8879"}],"version-history":[{"count":1,"href":"https:\/\/telecomkh.info\/index.php?rest_route=\/wp\/v2\/posts\/8879\/revisions"}],"predecessor-version":[{"id":8881,"href":"https:\/\/telecomkh.info\/index.php?rest_route=\/wp\/v2\/posts\/8879\/revisions\/8881"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/telecomkh.info\/index.php?rest_route=\/wp\/v2\/media\/8880"}],"wp:attachment":[{"href":"https:\/\/telecomkh.info\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=8879"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/telecomkh.info\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=8879"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/telecomkh.info\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=8879"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}