{"id":588730,"date":"2026-08-10T08:44:21","date_gmt":"2026-08-10T08:44:21","guid":{"rendered":"https:\/\/www.newsbeep.com\/ie\/588730\/"},"modified":"2026-08-10T08:44:21","modified_gmt":"2026-08-10T08:44:21","slug":"deep-learning-refines-how-bionic-eyes-communicate-with-the-brain","status":"publish","type":"post","link":"https:\/\/www.newsbeep.com\/ie\/588730\/","title":{"rendered":"Deep learning refines how bionic eyes communicate with the brain"},"content":{"rendered":"<p>            <a href=\"https:\/\/www.openaccessgovernment.org\/wp-content\/uploads\/2026\/08\/bionic-eye-pic.jpg\" data-caption=\"\u00a9 Matt Perko, UC Santa Barbara\" rel=\"nofollow noopener\" target=\"_blank\"><img loading=\"lazy\" decoding=\"async\" width=\"696\" height=\"380\" class=\"entry-thumb td-modal-image\" src=\"https:\/\/www.newsbeep.com\/ie\/wp-content\/uploads\/2026\/08\/bionic-eye-pic-696x380.jpg\"   alt=\"UCSB\u2019s Michael Beyeler is using AI to improve visual cortical prostheses, or \u201cbionic eyes.\" title=\"\"\/><\/a>\u00a9 Matt Perko, UC Santa Barbara<br \/>\n            Researchers from UC Santa Barbara, ETH Zurich, and Miguel Hern\u00e1ndez University demonstrated that artificial intelligence models can optimise electrical stimulation in visual cortical prostheses (bionic eyes), improving the accuracy, efficiency, and predictability of artificial vision<\/p>\n<p>Visual cortical prostheses or bionic eye skip the eyes and <a href=\"https:\/\/www.openaccessgovernment.org\/13-second-eye-test-predicts-consciousness-recovery-after-severe-brain-injury\/211042\/\" rel=\"nofollow noopener\" target=\"_blank\">optic nerves entirely,<\/a> delivering electrical stimulation directly to the visual cortex at the back of the brain. This approach offers potential benefits for individuals who lost vision due to traumatic brain injury, stroke, or neurodegenerative disease but retain a functional visual cortex.<\/p>\n<p>Key mechanical challenges of traditional prostheses include:<\/p>\n<p>Non-pixel behaviour: The brain does not process electrode signals as simple pixels; adjacent electrodes interact, and neural responses fluctuate over time.<br \/>\nPerceptual disconnect: Standard electrical stimulation settings fail to reliably predict what a user actually perceives (phosphenes, or spots of light).<\/p>\n<p>AI-driven neural control and human trial<\/p>\n<p>Published in Neuron, the study tested a deep-learning model on a 27-year-old blind participant in Spain implanted with a 96-channel cortical electrode array:<\/p>\n<p>Predictive modelling: Researchers trained a deep neural network on actual brain activity responses rather than fixed electrical parameters, incorporating the participant\u2019s resting brain state immediately prior to stimulation.<br \/>\nImproved efficiency: AI-designed stimulation patterns reproduced target brain activity more accurately while requiring significantly lower electrical current.<br \/>\nPerceptual accuracy: Recorded neural responses served as a far stronger predictor of perceived phosphene features (shape, size, brightness, colour) than raw electrode settings alone.<\/p>\n<p>Adaptive systems for long-term usability<\/p>\n<p><a href=\"https:\/\/news.ucsb.edu\/2026\/022739\/deep-learning-refines-how-bionic-eyes-communicate-brain\" target=\"_blank\" rel=\"noopener nofollow\">Because neural responses change daily, static stimulation settings cannot maintain reliable artificial vision.<\/a><\/p>\n<p>By integrating resting-state measurements and closed-loop neural feedback, the deep-learning framework allows the prosthesis to adapt to the individual user\u2019s shifting brain states in real time, moving away from rigid, one-size-fits-all stimulation protocols.<\/p>\n<p>\u201cA useful visual prosthesis cannot rely on a fixed recipe,\u201d Beyeler said. \u201cIt has to learn how an individual brain responds and adapt the stimulation accordingly. Ultimately, the device should adapt to the person, not the other way around.\u201d<\/p>\n","protected":false},"excerpt":{"rendered":"\u00a9 Matt Perko, UC Santa Barbara Researchers from UC Santa Barbara, ETH Zurich, and Miguel Hern\u00e1ndez University demonstrated&hellip;\n","protected":false},"author":2,"featured_media":588731,"comment_status":"","ping_status":"","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[10],"tags":[218,103,61,60,37098,248650],"class_list":["post-588730","post","type-post","status-publish","format-standard","has-post-thumbnail","category-health","tag-artificial-intelligence","tag-health","tag-ie","tag-ireland","tag-medical-treatment","tag-optical-health"],"_links":{"self":[{"href":"https:\/\/www.newsbeep.com\/ie\/wp-json\/wp\/v2\/posts\/588730","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.newsbeep.com\/ie\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.newsbeep.com\/ie\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.newsbeep.com\/ie\/wp-json\/wp\/v2\/users\/2"}],"replies":[{"embeddable":true,"href":"https:\/\/www.newsbeep.com\/ie\/wp-json\/wp\/v2\/comments?post=588730"}],"version-history":[{"count":0,"href":"https:\/\/www.newsbeep.com\/ie\/wp-json\/wp\/v2\/posts\/588730\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.newsbeep.com\/ie\/wp-json\/wp\/v2\/media\/588731"}],"wp:attachment":[{"href":"https:\/\/www.newsbeep.com\/ie\/wp-json\/wp\/v2\/media?parent=588730"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.newsbeep.com\/ie\/wp-json\/wp\/v2\/categories?post=588730"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.newsbeep.com\/ie\/wp-json\/wp\/v2\/tags?post=588730"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}