{"id":664650,"date":"2025-04-23T09:20:26","date_gmt":"2025-04-23T06:20:26","guid":{"rendered":"https:\/\/en.buradabiliyorum.com\/brain-inspired-ai-technique-mimics-human-visual-processing-to-enhance-machine-vision\/"},"modified":"2025-04-23T09:20:26","modified_gmt":"2025-04-23T06:20:26","slug":"brain-inspired-ai-technique-mimics-human-visual-processing-to-enhance-machine-vision","status":"publish","type":"post","link":"https:\/\/buradabiliyorum.com\/en\/brain-inspired-ai-technique-mimics-human-visual-processing-to-enhance-machine-vision\/","title":{"rendered":"Brain-inspired AI technique mimics human visual processing to enhance machine vision"},"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-6a2bfbd3b9d00\" 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-6a2bfbd3b9d00\" 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\/brain-inspired-ai-technique-mimics-human-visual-processing-to-enhance-machine-vision\/#Introducing_Lp-Convolution_A_smarter_way_to_see\" >Introducing Lp-Convolution: A smarter way to see<\/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\/brain-inspired-ai-technique-mimics-human-visual-processing-to-enhance-machine-vision\/#Real-world_performance_Stronger_smarter_and_more_robust_AI\" >Real-world performance: Stronger, smarter, and more robust AI<\/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\/brain-inspired-ai-technique-mimics-human-visual-processing-to-enhance-machine-vision\/#Impact_and_future_applications\" >Impact and future applications<\/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\/brain-inspired-ai-brea.jpg\" data-src=\"https:\/\/scx2.b-cdn.net\/gfx\/news\/2025\/brain-inspired-ai-brea.jpg\" data-sub-html=\"Information processing structures of the brain's visual cortex and artificial neural networks. In the actual brain's visual cortex, neurons are connected broadly and smoothly around a central point, with connection strength varying gradually with distance (a, b). This spatial connectivity follows a bell-shaped curve known as a &quot;Gaussian distribution,&quot; enabling the brain to integrate visual information not only from the center but also from the surrounding areas. In contrast, traditional Convolutional Neural Networks (CNNs) process information by having neurons focus on a fixed rectangular region (e.g., 3\u00d73, 5\u00d75, etc.) (c, d). CNN filters move across an image at regular intervals, extracting information in a uniform manner, which limits their ability to capture relationships between distant visual elements or respond selectively based on importance. This study addresses the differences between these biological structures and CNNs, proposing a new filter structure called &quot;Lp-Convolution&quot; that mimics the brain's connectivity patterns. In this structure, the range and sensitivity of a neuron's input are designed to naturally spread in a Gaussian-like form, allowing the system to self-adjust during training\u2014emphasizing important information more strongly while downplaying less relevant details. This enables image processing that is more flexible and biologically aligned compared to traditional CNNs. Credit: Institute for Basic Science\">\n<figure class=\"article-img\">\n            <img loading=\"lazy\" decoding=\"async\" src=\"https:\/\/scx1.b-cdn.net\/csz\/news\/800a\/2025\/brain-inspired-ai-brea.jpg\" alt=\"Brain-inspired AI breakthrough: Making computers see more like humans\" title=\"Information processing structures of the brain's visual cortex and artificial neural networks. In the actual brain's visual cortex, neurons are connected broadly and smoothly around a central point, with connection strength varying gradually with distance (a, b). This spatial connectivity follows a bell-shaped curve known as a &quot;Gaussian distribution,&quot; enabling the brain to integrate visual information not only from the center but also from the surrounding areas. In contrast, traditional Convolutional Neural Networks (CNNs) process information by having neurons focus on a fixed rectangular region (e.g., 3\u00d73, 5\u00d75, etc.) (c, d). CNN filters move across an image at regular intervals, extracting information in a uniform manner, which limits their ability to capture relationships between distant visual elements or respond selectively based on importance. This study addresses the differences between these biological structures and CNNs, proposing a new filter structure called &quot;Lp-Convolution&quot; that mimics the brain's connectivity patterns. In this structure, the range and sensitivity of a neuron's input are designed to naturally spread in a Gaussian-like form, allowing the system to self-adjust during training\u2014emphasizing important information more strongly while downplaying less relevant details. This enables image processing that is more flexible and biologically aligned compared to traditional CNNs. Credit: Institute for Basic Science\" width=\"800\" height=\"530\"\/><figcaption class=\"text-darken text-low-up text-truncate-js text-truncate mt-3\">\n                Information processing structures of the brain&#8217;s visual cortex and artificial neural networks. In the actual brain&#8217;s visual cortex, neurons are connected broadly and smoothly around a central point, with connection strength varying gradually with distance (a, b). This spatial connectivity follows a bell-shaped curve known as a &#8220;Gaussian distribution,&#8221; enabling the brain to integrate visual information not only from the center but also from the surrounding areas. In contrast, traditional Convolutional Neural Networks (CNNs) process information by having neurons focus on a fixed rectangular region (e.g., 3\u00d73, 5\u00d75, etc.) (c, d). CNN filters move across an image at regular intervals, extracting information in a uniform manner, which limits their ability to capture relationships between distant visual elements or respond selectively based on importance. This study addresses the differences between these biological structures and CNNs, proposing a new filter structure called &#8220;Lp-Convolution&#8221; that mimics the brain&#8217;s connectivity patterns. In this structure, the range and sensitivity of a neuron&#8217;s input are designed to naturally spread in a Gaussian-like form, allowing the system to self-adjust during training\u2014emphasizing important information more strongly while downplaying less relevant details. This enables image processing that is more flexible and biologically aligned compared to traditional CNNs. Credit: Institute for Basic <a href=\"https:\/\/buradabiliyorum.com\/en\/category\/sciencee\/\" data-internallinksmanager029f6b8e52c=\"5\" title=\"Science\" target=\"_blank\" rel=\"noopener\">Science<\/a><br \/>\n            <\/figcaption><\/figure>\n<\/p><\/div>\n<\/div>\n<p>A team of researchers from the Institute for Basic Science, Yonsei University, and the Max Planck Institute have developed a new artificial intelligence (AI) technique that brings machine vision closer to how the human brain processes images. Called Lp-Convolution, this method improves the accuracy and efficiency of image recognition systems while reducing the computational burden of existing AI models.<\/p>\n<p>The human brain is remarkably efficient at identifying key details in complex scenes, an ability that traditional AI systems have struggled to replicate. Convolutional Neural Networks (CNNs)\u2014the most widely used AI model for image recognition\u2014process images using small, square-shaped filters. While effective, this rigid <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>roach limits their ability to capture broader patterns in fragmented data.<\/p>\n<p>More recently, vision transformers have shown superior performance by analyzing entire images at once, but they require massive computational power and large datasets, making them impractical for many real-world applications.<\/p>\n<p>Inspired by how the brain&#8217;s visual cortex processes information selectively through circular, sparse connections, the research team sought a middle ground: Could a brain-like approach make CNNs both efficient and powerful?<\/p>\n<h2><span class=\"ez-toc-section\" id=\"Introducing_Lp-Convolution_A_smarter_way_to_see\"><\/span>Introducing Lp-Convolution: A smarter way to see<span class=\"ez-toc-section-end\"><\/span><\/h2>\n<p>To answer this, the team developed Lp-Convolution, a novel method that uses a multivariate p-<a href=\"https:\/\/buradabiliyorum.com\/en\/category\/general\/\" data-internallinksmanager029f6b8e52c=\"3\" title=\"General\" target=\"_blank\" rel=\"noopener\">general<\/a>ized normal distribution (MPND) to reshape CNN filters dynamically. Unlike traditional CNNs, which use fixed square filters, Lp-Convolution allows AI models to adapt their filter shapes\u2014stretching horizontally or vertically based on the task, much like how the human brain selectively focuses on relevant details.<\/p>\n<p>This breakthrough solves a long-standing challenge in AI research, known as the large kernel problem. Simply increasing filter sizes in CNNs (e.g., using 7\u00d77 or larger kernels) usually does not improve performance, despite adding more parameters. Lp-Convolution overcomes this limitation by introducing flexible, biologically inspired connectivity patterns.<\/p>\n<div class=\"article-gallery lightGallery\">\n<div data-thumb=\"https:\/\/scx1.b-cdn.net\/csz\/news\/tmb\/2025\/brain-inspired-ai-brea-1.jpg\" data-src=\"https:\/\/scx2.b-cdn.net\/gfx\/news\/2025\/brain-inspired-ai-brea-1.jpg\" data-sub-html=\"Brain-inspired design of Lp-Convolution. The brain processes visual information using a Gaussian-shaped connectivity structure that gradually spreads from the center outward, flexibly integrating a wide range of information. In contrast, traditional CNNs face issues where expanding the filter size dilutes information or reduces accuracy (d, e).To overcome these structural limitations, the research team developed Lp-Convolution, inspired by the brain\u2019s connectivity (a\u2013c). This design spatially distributes weights to preserve key information even over large receptive fields, effectively addressing the shortcomings of conventional CNNs. Credit: Institute for Basic Science\">\n<figure class=\"article-img text-center\">\n            <img decoding=\"async\" src=\"https:\/\/scx1.b-cdn.net\/csz\/news\/800a\/2025\/brain-inspired-ai-brea-1.jpg\" alt=\"Brain-inspired AI breakthrough: Making computers see more like humans\" title=\"Brain-inspired design of Lp-Convolution. The brain processes visual information using a Gaussian-shaped connectivity structure that gradually spreads from the center outward, flexibly integrating a wide range of information. In contrast, traditional CNNs face issues where expanding the filter size dilutes information or reduces accuracy (d, e).To overcome these structural limitations, the research team developed Lp-Convolution, inspired by the brain\u2019s connectivity (a\u2013c). This design spatially distributes weights to preserve key information even over large receptive fields, effectively addressing the shortcomings of conventional CNNs. Credit: Institute for Basic Science\"\/><figcaption class=\"text-left text-darken text-truncate text-low-up mt-3\">\n                Brain-inspired design of Lp-Convolution. The brain processes visual information using a Gaussian-shaped connectivity structure that gradually spreads from the center outward, flexibly integrating a wide range of information. In contrast, traditional CNNs face issues where expanding the filter size dilutes information or reduces accuracy (d, e).To overcome these structural limitations, the research team developed Lp-Convolution, inspired by the brain\u2019s connectivity (a\u2013c). This design spatially distributes weights to preserve key information even over large receptive fields, effectively addressing the shortcomings of conventional CNNs. Credit: Institute for Basic Science<br \/>\n            <\/figcaption><\/figure>\n<\/p><\/div>\n<\/div>\n<p>                                                                                                        <!-- TechX - News - In-article --><\/p>\n<h2><span class=\"ez-toc-section\" id=\"Real-world_performance_Stronger_smarter_and_more_robust_AI\"><\/span>Real-world performance: Stronger, smarter, and more robust AI<span class=\"ez-toc-section-end\"><\/span><\/h2>\n<p>In tests on standard image classification datasets (CIFAR-100, TinyImageNet), Lp-Convolution significantly improved accuracy on both classic models like AlexNet and modern architectures like RepLKNet. The method also proved to be highly robust against corrupted data, a major challenge in real-world AI applications.<\/p>\n<p>Moreover, the researchers found that when the Lp-masks used in their method resembled a Gaussian distribution, the AI&#8217;s internal processing patterns closely matched biological neural activity, as confirmed through comparisons with mouse brain data.<\/p>\n<p>&#8220;We humans quickly spot what matters in a crowded scene,&#8221; said Dr. C. Justin Lee, Director of the Center for Cognition and <a href=\"https:\/\/buradabiliyorum.com\/en\/category\/social-mediaa\/\" data-internallinksmanager029f6b8e52c=\"1\" title=\"Social Media\" target=\"_blank\" rel=\"noopener\">Social<\/a>ity within the Institute for Basic Science. &#8220;Our Lp-Convolution mimics this ability, allowing AI to flexibly focus on the most relevant parts of an image\u2014just like the brain does.&#8221;<\/p>\n<h2><span class=\"ez-toc-section\" id=\"Impact_and_future_applications\"><\/span>Impact and future applications<span class=\"ez-toc-section-end\"><\/span><\/h2>\n<p>Unlike previous efforts that either relied on small, rigid filters or required resource-heavy transformers, Lp-Convolution offers a practical, efficient alternative. This innovation could revolutionize fields such as:<\/p>\n<ul>\n<li>Autonomous driving, where AI must quickly detect obstacles in real time<\/li>\n<li>Medical imaging, improving AI-based diagnoses by highlighting subtle details<\/li>\n<li>Robotics, enabling smarter and more adaptable machine vision under changing conditions<\/li>\n<\/ul>\n<p>&#8220;This work is a powerful contribution to both AI and neuroscience,&#8221; said Director Lee. &#8220;By aligning AI more closely with the brain, we&#8217;ve unlocked new potential for CNNs, making them smarter, more adaptable, and more biologically realistic.&#8221;<\/p>\n<p>Looking ahead, the team plans to refine this <a href=\"https:\/\/buradabiliyorum.com\/en\/category\/technology\/\" data-internallinksmanager029f6b8e52c=\"4\" title=\"Technology\" target=\"_blank\" rel=\"noopener\">technology<\/a> further, exploring its applications in complex reasoning tasks such as puzzle-solving (e.g., Sudoku) and real-time image processing.<\/p>\n<p>The study will be presented at the International Conference on Learning Representations (<a rel=\"nofollow\" target=\"_blank\" href=\"https:\/\/iclr.cc\/\" target=\"_blank\">ICLR 2025<\/a>), and the research team has made their code and models publicly available on <a rel=\"nofollow\" target=\"_blank\" href=\"https:\/\/github.com\/jeakwon\/lpconv\/\" target=\"_blank\">GitHub<\/a> and <a rel=\"nofollow\" target=\"_blank\" href=\"https:\/\/openreview.net\/forum?id=0LSAmFCc4p\" target=\"_blank\">OpenReview.net<\/a>.<\/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\tBrain-inspired \ud835\udc3f\ud835\udc5d-Convolution benefits large kernels and aligns better with visual cortex. <a rel=\"nofollow\" target=\"_blank\" href=\"https:\/\/openreview.net\/forum?id=0LSAmFCc4p\" target=\"_blank\">openreview.net\/forum?id=0LSAmFCc4p<\/a><\/p>\n<\/div>\n<div class=\"d-inline-block text-medium my-4\">\n                                                Provided by<br \/>\n                                                                                                    Institute for Basic Science<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.ibs.re.kr\/en\/\" 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                                                Brain-inspired AI technique mimics human visual processing to enhance machine vision (2025, April 22)<br \/>\n                                                retrieved 23 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-brain-ai-technique-mimics-human.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-brain-ai-technique-mimics-human.html\" target=\"_blank\" >Source<\/a><\/span><\/p>\n","protected":false},"excerpt":{"rendered":"<p>Information processing structures of the brain&#8217;s visual cortex and artificial neural networks. In the actual brain&#8217;s visual cortex, neurons are connected broadly and smoothly around a central point, with connection strength varying gradually with distance (a, b). This spatial connectivity follows a bell-shaped curve known as a &#8220;Gaussian distribution,&#8221; enabling the brain to integrate visual&#8230;<\/p>\n","protected":false},"author":1,"featured_media":664651,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"fifu_image_url":"https:\/\/scx2.b-cdn.net\/gfx\/news\/2025\/brain-inspired-ai-brea.jpg","fifu_image_alt":"","footnotes":""},"categories":[16],"tags":[],"class_list":["post-664650","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\/664650","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=664650"}],"version-history":[{"count":0,"href":"https:\/\/buradabiliyorum.com\/en\/wp-json\/wp\/v2\/posts\/664650\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/buradabiliyorum.com\/en\/wp-json\/wp\/v2\/media\/664651"}],"wp:attachment":[{"href":"https:\/\/buradabiliyorum.com\/en\/wp-json\/wp\/v2\/media?parent=664650"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/buradabiliyorum.com\/en\/wp-json\/wp\/v2\/categories?post=664650"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/buradabiliyorum.com\/en\/wp-json\/wp\/v2\/tags?post=664650"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}