{"id":181401,"date":"2024-01-25T20:31:41","date_gmt":"2024-01-26T02:31:41","guid":{"rendered":"https:\/\/lifeboat.com\/blog\/2024\/01\/programming-light-propagation-creates-highly-efficient-neural-networks"},"modified":"2024-01-25T20:31:41","modified_gmt":"2024-01-26T02:31:41","slug":"programming-light-propagation-creates-highly-efficient-neural-networks","status":"publish","type":"post","link":"https:\/\/lifeboat.com\/blog\/2024\/01\/programming-light-propagation-creates-highly-efficient-neural-networks","title":{"rendered":"Programming light propagation creates highly efficient neural networks"},"content":{"rendered":"<p><a class=\"aligncenter blog-photo\" href=\"https:\/\/lifeboat.com\/blog.images\/programming-light-propagation-creates-highly-efficient-neural-networks3.jpg\"><\/a><\/p>\n<p>Current artificial intelligence models utilize billions of trainable parameters to achieve challenging tasks. However, this large number of parameters comes with a hefty cost. Training and deploying these huge models require immense memory space and computing capability that can only be provided by hangar-sized data centers in processes that consume energy equivalent to the electricity needs of midsized cities.<\/p>\n<p>The <a href=\"https:\/\/techxplore.com\/tags\/research+community\/\" rel=\"tag\" class=\"\">research community<\/a> is presently making efforts to rethink both the related computing hardware and the machine learning algorithms to sustainably keep the development of <a href=\"https:\/\/techxplore.com\/tags\/artificial+intelligence\/\" rel=\"tag\" class=\"\">artificial intelligence<\/a> at its current pace. Optical implementation of neural network architectures is a promising avenue because of the low power implementation of the connections between the units.<\/p>\n<p>New research <a href=\"https:\/\/www.spiedigitallibrary.org\/journals\/advanced-photonics\/volume-6\/issue-01\/016002\/Programming-nonlinear-propagation-for-efficient-optical-learning-machines\/10.1117\/1.AP.6.1.016002.full\">reported in <i>Advanced Photonics<\/i><\/a> combines light propagation inside multimode fibers with a small number of digitally programmable parameters and achieves the same performance on image classification tasks with fully digital systems with more than 100 times more programmable parameters. This <a href=\"https:\/\/techxplore.com\/tags\/computational+framework\/\" rel=\"tag\" class=\"\">computational framework<\/a> streamlines the memory requirement and reduces the need for energy-intensive digital processes, while achieving the same level of accuracy in a variety of machine learning tasks.<\/p>\n","protected":false},"excerpt":{"rendered":"<p>Current artificial intelligence models utilize billions of trainable parameters to achieve challenging tasks. However, this large number of parameters comes with a hefty cost. Training and deploying these huge models require immense memory space and computing capability that can only be provided by hangar-sized data centers in processes that consume energy equivalent to the electricity [\u2026]<\/p>\n","protected":false},"author":599,"featured_media":0,"comment_status":"open","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[41,6,8],"tags":[],"class_list":["post-181401","post","type-post","status-publish","format-standard","hentry","category-information-science","category-robotics-ai","category-space"],"_links":{"self":[{"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/posts\/181401","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/users\/599"}],"replies":[{"embeddable":true,"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/comments?post=181401"}],"version-history":[{"count":0,"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/posts\/181401\/revisions"}],"wp:attachment":[{"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/media?parent=181401"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/categories?post=181401"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/tags?post=181401"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}