{"id":663002,"date":"2025-04-16T09:00:32","date_gmt":"2025-04-16T06:00:32","guid":{"rendered":"https:\/\/en.buradabiliyorum.com\/programmable-photonic-chip-uses-light-to-accelerate-ai-training-and-cut-energy-use\/"},"modified":"2025-04-16T09:00:32","modified_gmt":"2025-04-16T06:00:32","slug":"programmable-photonic-chip-uses-light-to-accelerate-ai-training-and-cut-energy-use","status":"publish","type":"post","link":"https:\/\/buradabiliyorum.com\/en\/programmable-photonic-chip-uses-light-to-accelerate-ai-training-and-cut-energy-use\/","title":{"rendered":"Programmable photonic chip uses light to accelerate AI training and cut energy use"},"content":{"rendered":"<div id=\"ez-toc-container\" class=\"ez-toc-v2_0_85 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-6a34d5d67a14b\" 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-6a34d5d67a14b\" 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-2'><a class=\"ez-toc-link ez-toc-heading-1\" href=\"https:\/\/buradabiliyorum.com\/en\/programmable-photonic-chip-uses-light-to-accelerate-ai-training-and-cut-energy-use\/#The_missing_piece_in_photonic_AI\" >The missing piece in photonic AI<\/a><\/li><li class='ez-toc-page-1 ez-toc-heading-level-2'><a class=\"ez-toc-link ez-toc-heading-2\" href=\"https:\/\/buradabiliyorum.com\/en\/programmable-photonic-chip-uses-light-to-accelerate-ai-training-and-cut-energy-use\/#Reshaping_light_with_light\" >Reshaping light with light<\/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\/programmable-photonic-chip-uses-light-to-accelerate-ai-training-and-cut-energy-use\/#Training_at_the_speed_of_light\" >Training at the speed of light<\/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\/programmable-photonic-chip-uses-light-to-accelerate-ai-training-and-cut-energy-use\/#Future_directions\" >Future directions<\/a><\/li><\/ul><\/nav><\/div>\n<div>\n<div class=\"article-gallery lightGallery\">\n<div data-thumb=\"https:\/\/scx1.b-cdn.net\/csz\/news\/tmb\/2025\/penn-engineers-first-t-1.jpg\" data-src=\"https:\/\/scx2.b-cdn.net\/gfx\/news\/2025\/penn-engineers-first-t-1.jpg\" data-sub-html=\"An image of the light inside the chip \u2014 the white dashed boxes are the inputs and the yellow dashed boxes the outputs. Credit: Liang Feng, Tianwei Wu\">\n<figure class=\"article-img\">\n            <img loading=\"lazy\" decoding=\"async\" src=\"https:\/\/scx1.b-cdn.net\/csz\/news\/800a\/2025\/penn-engineers-first-t-1.jpg\" alt=\"Penn engineers first to train AI at lightspeed\" title=\"An image of the light inside the chip \u2014 the white dashed boxes are the inputs and the yellow dashed boxes the outputs. Credit: Liang Feng, Tianwei Wu\" width=\"800\" height=\"530\"\/><figcaption class=\"text-darken text-low-up text-truncate-js text-truncate mt-3\">\n                An image of the light inside the chip \u2014 the white dashed boxes are the inputs and the yellow dashed boxes the outputs. Credit: Liang Feng, Tianwei Wu<br \/>\n            <\/figcaption><\/figure>\n<\/p><\/div>\n<\/div>\n<p>Penn Engineers have developed the first programmable chip that can train nonlinear neural networks using light\u2014a breakthrough that could dramatically speed up AI training, reduce energy use and even pave the way for fully light-powered computers.<\/p>\n<p>While today&#8217;s AI chips are electronic and rely on electricity to perform calculations, the new chip is photonic, meaning it uses beams of light instead. Described in <i><a rel=\"nofollow\" target=\"_blank\" href=\"https:\/\/www.nature.com\/articles\/s41566-025-01660-x\" target=\"_blank\">Nature Photonics<\/a><\/i>, the chip reshapes how light behaves to carry out the nonlinear mathematics at the heart of modern AI.<\/p>\n<p>&#8220;Nonlinear functions are critical for training deep neural networks,&#8221; says Liang Feng, Professor in Materials <a href=\"https:\/\/buradabiliyorum.com\/en\/category\/sciencee\/\" data-internallinksmanager029f6b8e52c=\"5\" title=\"Science\" target=\"_blank\" rel=\"noopener\">Science<\/a> and Engineering (MSE) and in Electrical and Systems Engineering (ESE), and the paper&#8217;s senior author. &#8220;Our aim was to make this h<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>en in photonics for the first time.&#8221;<\/p>\n<h2><span class=\"ez-toc-section\" id=\"The_missing_piece_in_photonic_AI\"><\/span>The missing piece in photonic AI<span class=\"ez-toc-section-end\"><\/span><\/h2>\n<p>Most AI systems today depend on neural networks, software designed to mimic biological neural tissue. Just as neurons connect to allow biological creatures to think, neural networks link together layers of simple units, or &#8220;nodes,&#8221; enabling AI systems to perform complex tasks.<\/p>\n<p>In both artificial and biological systems, these nodes only &#8220;fire&#8221; once a threshold is reached\u2014a nonlinear process that allows small changes in input to cause larger, more complex changes in output.<\/p>\n<p>Without that nonlinearity, adding layers does nothing: the system just reduces to a single-layer linear operation, where inputs are simply added together, and no real learning occurs.<\/p>\n<p>While many research teams, <a rel=\"nofollow\" target=\"_blank\" href=\"https:\/\/phys.org\/news\/2024-02-chip-door-ai.html\" target=\"_blank\">including teams at Penn Engineering<\/a>, have developed light-powered chips capable of handling linear mathematical operations, none has solved the challenge of representing nonlinear functions using only light\u2014until now.<\/p>\n<p>&#8220;Without nonlinear functions, photonic chips can&#8217;t train deep networks or perform truly intelligent tasks,&#8221; says Tianwei Wu (Gr&#8217;24), a postdoctoral fellow in ESE and the paper&#8217;s first author.<\/p>\n<p>                                                                                                        <!-- TechX - News - In-article --><\/p>\n<h2><span class=\"ez-toc-section\" id=\"Reshaping_light_with_light\"><\/span>Reshaping light with light<span class=\"ez-toc-section-end\"><\/span><\/h2>\n<p>The team&#8217;s breakthrough begins with a special semiconductor material that responds to light. When a beam of &#8220;signal&#8221; light (carrying the input data) passes through the material, a second &#8220;pump&#8221; beam shines in from above, adjusting how the material reacts.<\/p>\n<p>By changing the shape and intensity of the pump beam, the team can control how the signal light is absorbed, transmitted or amplified, depending on its intensity and the material&#8217;s behavior. This process &#8220;programs&#8221; the chip to perform different nonlinear functions.<\/p>\n<div class=\"article-gallery lightGallery\">\n<div data-thumb=\"https:\/\/scx1.b-cdn.net\/csz\/news\/tmb\/2025\/penn-engineers-first-t.jpg\" data-src=\"https:\/\/scx2.b-cdn.net\/gfx\/news\/hires\/2025\/penn-engineers-first-t.jpg\" data-sub-html=\"Postdoctoral fellow Tianwei Wu (left) and Professor Liang Feng (right) in the lab, demonstrating some of the apparatus used to develop the new, light-powered chip. Credit: Sylvia Zhang.\">\n<figure class=\"article-img text-center\">\n            <img decoding=\"async\" src=\"https:\/\/scx1.b-cdn.net\/csz\/news\/800a\/2025\/penn-engineers-first-t.jpg\" alt=\"Penn engineers first to train AI at lightspeed\" title=\"Postdoctoral fellow Tianwei Wu (left) and Professor Liang Feng (right) in the lab, demonstrating some of the apparatus used to develop the new, light-powered chip. Credit: Sylvia Zhang.\"\/><figcaption class=\"text-left text-darken text-truncate text-low-up mt-3\">\n                Postdoctoral fellow Tianwei Wu (left) and Professor Liang Feng (right) in the lab, demonstrating some of the apparatus used to develop the new, light-powered chip. Credit: Sylvia Zhang.<br \/>\n            <\/figcaption><\/figure>\n<\/p><\/div>\n<\/div>\n<p>&#8220;We&#8217;re not changing the chip&#8217;s structure,&#8221; says Feng. &#8220;We&#8217;re using light itself to create patterns inside the material, which then reshapes how the light moves through it.&#8221;<\/p>\n<p>The result is a reconfigurable system that can express a wide range of mathematical functions depending on the pump pattern. That flexibility allows the chip to learn in real time, adjusting its behavior based on feedback from its output.<\/p>\n<h2><span class=\"ez-toc-section\" id=\"Training_at_the_speed_of_light\"><\/span>Training at the speed of light<span class=\"ez-toc-section-end\"><\/span><\/h2>\n<p>To test the chip&#8217;s potential, the team used the chip to solve benchmark AI problems. The platform achieved over 97% accuracy on a simple nonlinear decision boundary task and over 96% on the well-known Iris flower data set\u2014a machine learning standard.<\/p>\n<p>In both cases, the photonic chip matched or outperformed traditional digital neural networks, but used fewer operations, and did not need power-hungry electronic components.<\/p>\n<p>In one striking result, just four nonlinear optical connections on the chip were equivalent to 20 linear electronic connections with fixed nonlinear activation functions in a traditional model. That efficiency hints at what&#8217;s possible as the architecture scales.<\/p>\n<p>Unlike previous photonic systems\u2014which are fixed after fabrication\u2014the Penn chip starts as a blank canvas. The pump light acts like a brush, drawing reprogrammable instructions into the material.<\/p>\n<p>&#8220;This is a true proof-of-concept for a field-programmable photonic computer,&#8221; says Feng. &#8220;It&#8217;s a step toward a future where we can train AI at the speed of light.&#8221;<\/p>\n<h2><span class=\"ez-toc-section\" id=\"Future_directions\"><\/span>Future directions<span class=\"ez-toc-section-end\"><\/span><\/h2>\n<p>While the current work focuses on polynomials\u2014a flexible family of functions widely used in machine learning\u2014the team believes their approach could enable even more powerful operations in the future, such as exponential or inverse functions. That would pave the way for photonic systems that tackle large-scale tasks like training large language models.<\/p>\n<p>By replacing heat-generating electronics with low-energy optical components, the platform also promises to slash energy consumption in AI data centers\u2014potentially transforming the economics of machine learning.<\/p>\n<p>&#8220;This could be the beginning of photonic computing as a serious alternative to electronics,&#8221; says Liang. &#8220;Penn is the birthplace of ENIAC, the world&#8217;s first digital computer\u2014this chip might be the first real step toward a photonic ENIAC.&#8221;<\/p>\n<div class=\"article-main__more p-4\">\n<p><strong>More information:<\/strong><br \/>\n\t\t\t\t\t\t\t\t\t\t\t\tTianwei Wu et al, Field-programmable photonic nonlinearity, <i>Nature Photonics<\/i> (2025). <a rel=\"nofollow\" target=\"_blank\" data-doi=\"1\" href=\"https:\/\/dx.doi.org\/10.1038\/s41566-025-01660-x\" target=\"_blank\">DOI: 10.1038\/s41566-025-01660-x<\/a><\/p>\n<\/p><\/div>\n<div class=\"d-inline-block text-medium my-4\">\n                                                Provided by<br \/>\n                                                                                                    University of Pennsylvania<br \/>\n                                                    \t\t\t\t\t\t\t\t\t\t\t\t\t<a rel=\"nofollow\" target=\"_blank\" class=\"icon_open\" href=\"http:\/\/www.upenn.edu\/\" target=\"_blank\" rel=\"nofollow\"><br \/>\n\t\t\t\t\t\t\t\t\t\t\t\t\t\t<svg>\n\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t<use href=\"https:\/\/techx.b-cdn.net\/tmpl\/v2\/img\/svg\/sprite.svg#icon_open\" x=\"0\" y=\"0\"\/>\n\t\t\t\t\t\t\t\t\t\t\t\t\t\t<\/svg><br \/>\n\t\t\t\t\t\t\t\t\t\t\t\t\t<\/a><\/p><\/div>\n<p>                                        <!-- print only --><\/p>\n<div class=\"d-none d-print-block\">\n<p>\n                                                <strong>Citation<\/strong>:<br \/>\n                                                Programmable photonic chip uses light to accelerate AI training and cut energy use (2025, April 15)<br \/>\n                                                retrieved 16 April 2025<br \/>\n                                                from https:\/\/techxplore.com\/<a href=\"https:\/\/buradabiliyorum.com\/en\/category\/news\/\" data-internallinksmanager029f6b8e52c=\"2\" title=\"News\" target=\"_blank\" rel=\"noopener\">news<\/a>\/2025-04-programmable-photonic-chip-ai-energy.html\n                                            <\/p>\n<p>\n                                            This document is subject to copyright. Apart from any fair dealing for the purpose of private study or research, no<br \/>\n                                            part may be reproduced without the written permission. The content is provided for information purposes only.\n                                            <\/p>\n<\/p><\/div>\n<\/p><\/div>\n<p><script id=\"facebook-jssdk\" async=\"\" src=\"https:\/\/connect.facebook.net\/en_US\/sdk.js\"><\/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\/CAAqBwgKMN63nwsw68G3Aw\" 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;\"><strong>If you want to read more Like this articles, you can visit our <span style=\"color: #ff9900;\"><a style=\"color: #ff9900;\" href=\"https:\/\/en.buradabiliyorum.com\/category\/sciencee\/\" target=\"_blank\" >Science category.<\/a><\/span><\/strong><\/p>\n<\/blockquote>\n<p><span style=\"color: black;\"><a style=\"color: #ff9900;\" href=\"https:\/\/techxplore.com\/news\/2025-04-programmable-photonic-chip-ai-energy.html\" target=\"_blank\" >Source<\/a><\/span><\/p>\n","protected":false},"excerpt":{"rendered":"<p>An image of the light inside the chip \u2014 the white dashed boxes are the inputs and the yellow dashed boxes the outputs. Credit: Liang Feng, Tianwei Wu Penn Engineers have developed the first programmable chip that can train nonlinear neural networks using light\u2014a breakthrough that could dramatically speed up AI training, reduce energy use&#8230;<\/p>\n","protected":false},"author":1,"featured_media":663003,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"fifu_image_url":"https:\/\/scx2.b-cdn.net\/gfx\/news\/2025\/penn-engineers-first-t-1.jpg","fifu_image_alt":"","footnotes":""},"categories":[16],"tags":[],"class_list":["post-663002","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-sciencee"],"_links":{"self":[{"href":"https:\/\/buradabiliyorum.com\/en\/wp-json\/wp\/v2\/posts\/663002","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=663002"}],"version-history":[{"count":0,"href":"https:\/\/buradabiliyorum.com\/en\/wp-json\/wp\/v2\/posts\/663002\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/buradabiliyorum.com\/en\/wp-json\/wp\/v2\/media\/663003"}],"wp:attachment":[{"href":"https:\/\/buradabiliyorum.com\/en\/wp-json\/wp\/v2\/media?parent=663002"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/buradabiliyorum.com\/en\/wp-json\/wp\/v2\/categories?post=663002"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/buradabiliyorum.com\/en\/wp-json\/wp\/v2\/tags?post=663002"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}