{"id":458512,"date":"2022-06-06T15:45:00","date_gmt":"2022-06-06T12:45:00","guid":{"rendered":"https:\/\/en.buradabiliyorum.com\/how-neural-networks-learn-differently-than-the-human-brain\/"},"modified":"2022-06-06T15:45:00","modified_gmt":"2022-06-06T12:45:00","slug":"how-neural-networks-learn-differently-than-the-human-brain","status":"publish","type":"post","link":"https:\/\/buradabiliyorum.com\/en\/how-neural-networks-learn-differently-than-the-human-brain\/","title":{"rendered":"#How neural networks &#8216;learn&#8217; differently than the human brain"},"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-6a3c5e29b03fc\" 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-6a3c5e29b03fc\" 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-1'><a class=\"ez-toc-link ez-toc-heading-1\" href=\"https:\/\/buradabiliyorum.com\/en\/how-neural-networks-learn-differently-than-the-human-brain\/#%E2%80%9CHow_neural_networks_%E2%80%98learn_differently_than_the_human_brain%E2%80%9D\" >&#8220;How neural networks &#8216;learn&#8217; differently than the human brain&#8221;<\/a><ul class='ez-toc-list-level-2' ><li class='ez-toc-heading-level-2'><a class=\"ez-toc-link ez-toc-heading-2\" href=\"https:\/\/buradabiliyorum.com\/en\/how-neural-networks-learn-differently-than-the-human-brain\/#A_widespread_misconception\" >A widespread misconception<\/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\/how-neural-networks-learn-differently-than-the-human-brain\/#Greetings_humanoids\" >Greetings humanoids<\/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\/how-neural-networks-learn-differently-than-the-human-brain\/#Neural_nets_vs_the_human_brain\" >Neural nets vs the human brain<\/a><\/li><li class='ez-toc-page-1 ez-toc-heading-level-2'><a class=\"ez-toc-link ez-toc-heading-5\" href=\"https:\/\/buradabiliyorum.com\/en\/how-neural-networks-learn-differently-than-the-human-brain\/#Neural_nets_can_learn_in_ways_we_cant\" >Neural nets can learn in ways we can\u2019t<\/a><\/li><\/ul><\/li><\/ul><\/nav><\/div>\n<h1><span class=\"ez-toc-section\" id=\"%E2%80%9CHow_neural_networks_%E2%80%98learn_differently_than_the_human_brain%E2%80%9D\"><\/span>&#8220;How neural networks &#8216;learn&#8217; differently than the human brain&#8221;<span class=\"ez-toc-section-end\"><\/span><\/h1>\n<div>\n                            Recently developed artificial intelligence (AI) models are capable of many impressive feats, including recognizing images and producing human-like language. But just because AI can perform human-like behaviors doesn\u2019t mean it can think or understand like humans.<\/p>\n<p>As a researcher studying how humans understand and reason about the world, I think it\u2019s important to emphasize the way AI systems \u201cthink\u201d and learn is fundamentally different to how humans do \u2013 and we have a long way to go before AI can truly think like us.<\/p>\n<h2><span class=\"ez-toc-section\" id=\"A_widespread_misconception\"><\/span>A widespread misconception<span class=\"ez-toc-section-end\"><\/span><\/h2>\n<p>Developments in AI have produced systems that can perform very human-like behaviors. The language model <a rel=\"nofollow noopener\" target=\"_blank\" href=\"https:\/\/www.twilio.com\/blog\/ultimate-guide-openai-gpt-3-language-model\">GPT-3<\/a> can produce text that\u2019s often indistinguishable from human speech. Another model, <a rel=\"nofollow noopener\" target=\"_blank\" href=\"https:\/\/ai.googleblog.com\/2022\/04\/pathways-language-model-palm-scaling-to.html\">PaLM<\/a>, can produce explanations for jokes it has never <a rel=\"nofollow noopener\" target=\"_blank\" href=\"https:\/\/www.cnet.com\/tech\/services-and-software\/no-joke-googles-ai-is-smart-enough-to-understand-your-humor\/\">seen before<\/a>.<\/p>\n<div class=\"corona-wrapper neural-cta hs-embed-tnw\">\n<div class=\"neural-cta-wrapper\">\n<div class=\"neural-cta-img\"><img decoding=\"async\" src=\"https:\/\/s3.amazonaws.com\/events.tnw\/hardfork-2018\/uploads\/companies\/neural-newsletter_header.gif\"\/><\/div>\n<p><noscript><img decoding=\"async\" src=\"https:\/\/s3.amazonaws.com\/events.tnw\/hardfork-2018\/uploads\/companies\/neural-newsletter_header.gif\"\/><\/noscript><\/p>\n<div class=\"neural-cta-input\">\n<h2 class=\"neural-cta-title\"><span class=\"ez-toc-section\" id=\"Greetings_humanoids\"><\/span>Greetings humanoids<span class=\"ez-toc-section-end\"><\/span><\/h2>\n<p class=\"neural-cta-tagline\">Subscribe now for a weekly recap of our favorite AI stories<\/p>\n<p><!--[if lte IE 8]><![endif]--><\/div>\n<\/div>\n<\/div>\n<p>Most recently, a <a href=\"https:\/\/buradabiliyorum.com\/en\/category\/general\/\" data-internallinksmanager029f6b8e52c=\"3\" title=\"General\" target=\"_blank\" rel=\"noopener\">general<\/a>-purpose AI known as Gato has been developed which can <a rel=\"nofollow noopener\" target=\"_blank\" href=\"https:\/\/www.zdnet.com\/article\/deepminds-gato-is-mediocre-so-why-did-they-build-it\/\">perform hundreds of tasks<\/a>, including captioning images, answering questions, playing Atari video <a href=\"https:\/\/buradabiliyorum.com\/en\/category\/game\/\" data-internallinksmanager029f6b8e52c=\"7\" title=\"Game\" target=\"_blank\" rel=\"noopener\">game<\/a>s, and even controlling a robot arm to stack blocks. And DALL-E is a system which has been trained to produce modified images and artwork from a text de<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\">script<\/a>ion.<\/p>\n<p>These breakthroughs have led to some bold claims about the capability of such AI, and what it can tell us about human intelligence.<\/p>\n<p>For example Nando de Freitas, a researcher at Google\u2019s AI company DeepMind, argues scaling up existing models will be enough to produce human-level artificial intelligence. Others have <a rel=\"nofollow noopener\" target=\"_blank\" href=\"https:\/\/medium.com\/@blaisea\/do-large-language-models-understand-us-6f881d6d8e75\">echoed<\/a> this view.<\/p>\n<p>In all the excitement, it\u2019s easy to assume human-like behavior means human-like understanding. But there are several key differences between how AI and humans think and learn.<\/p>\n<h2><span class=\"ez-toc-section\" id=\"Neural_nets_vs_the_human_brain\"><\/span>Neural nets vs the human brain<span class=\"ez-toc-section-end\"><\/span><\/h2>\n<p>Most recent AI is built from <a rel=\"nofollow noopener\" target=\"_blank\" href=\"https:\/\/theconversation.com\/what-is-a-neural-network-a-computer-scientist-explains-151897\">artificial neural networks<\/a>, or \u201cneural nets\u201d for short. The term \u201cneural\u201d is used because these networks are inspired by the human brain, in which billions of cells called neurons form complex webs of connections with one another, processing information as they fire signals back and forth.<\/p>\n<p>Neural nets are a highly simplified version of the biology. A real neuron is replaced with a simple node, and the strength of the connection between nodes is represented by a single number called a \u201cweight\u201d.<\/p>\n<p>With enough connected nodes stacked into enough layers, neural nets can be trained to recognize patterns and even \u201c<a rel=\"nofollow noopener\" target=\"_blank\" href=\"https:\/\/medium.com\/deep-learning-demystified\/generalization-in-neural-networks-7765ee42ac23\">generalize<\/a>\u201d to stimuli that are similar (but not identical) to what they\u2019ve seen before. Simply, generalization refers to an AI system\u2019s ability to take what it has learnt from certain data and apply it to new data.<\/p>\n<p>Being able to identify features, recognize patterns, and generalize from results lies at the heart of the success of neural nets \u2013 and mimics techniques humans use for such tasks. Yet there are important differences.<\/p>\n<p>Neural nets are typically trained by \u201c<a rel=\"nofollow noopener\" target=\"_blank\" href=\"https:\/\/www.ibm.com\/cloud\/learn\/supervised-learning\">supervised learning<\/a>\u201d. So they\u2019re presented with many examples of an input and the desired output, and then gradually the connection weights are adjusted until the network \u201clearns\u201d to produce the desired output.<\/p>\n<p>To learn a language task, a neural net may be presented with a sentence one word at a time, and will slowly learns to predict the next word in the sequence.<\/p>\n<p>This is very different from how humans typically learn. Most human learning is \u201cunsupervised\u201d, which means we\u2019re not explicitly told what the \u201cright\u201d response is for a given stimulus. We have to work this out ourselves.<\/p>\n<p>For instance, children aren\u2019t given instructions on how to speak, but learn this through a <a rel=\"nofollow noopener\" target=\"_blank\" href=\"https:\/\/www.abc.net.au\/education\/how-babies-learn-to-talk\/13757672\">complex process<\/a> of exposure to adult speech, imitation, and feedback.<\/p>\n<p>Another difference is the sheer scale of data used to train AI. The GPT-3 model was trained on <a rel=\"nofollow noopener\" target=\"_blank\" href=\"https:\/\/arxiv.org\/pdf\/2005.14165.pdf\">400 billion words<\/a>, mostly taken from the internet. At a rate of 150 words per minute, it would take a human nearly 4,000 years to read this much text.<\/p>\n<p>Such calculations show humans can\u2019t possibly learn the same way AI does. We have to make more efficient use of smaller amounts of data.<\/p>\n<h2><span class=\"ez-toc-section\" id=\"Neural_nets_can_learn_in_ways_we_cant\"><\/span>Neural nets can learn in ways we can\u2019t<span class=\"ez-toc-section-end\"><\/span><\/h2>\n<p>An even more fundamental difference concerns the way neural nets learn. In order to match up a stimulus with a desired response, neural nets use an algorithm called \u201cbackpropagation\u201d to pass errors backward through the network, allowing the weights to be adjusted in just the right way.<\/p>\n<p>However, it\u2019s widely recognized by neuroscientists that <a rel=\"nofollow noopener\" target=\"_blank\" href=\"https:\/\/www.nature.com\/articles\/s41583-020-0277-3\/\">backpropagation can\u2019t be implemented<\/a> in the brain, as it would require <a rel=\"nofollow noopener\" target=\"_blank\" href=\"https:\/\/journals.plos.org\/plosone\/article?id=10.1371\/journal.pone.0266102\">external signals<\/a> that just don\u2019t exist.<\/p>\n<p>Some researchers have proposed <a rel=\"nofollow noopener\" target=\"_blank\" href=\"https:\/\/www.sciencedirect.com\/science\/article\/pii\/S1364661319300129\">variations<\/a> of backpropagation could be used by the brain, but so far there is no evidence human brains can use such learning methods.<\/p>\n<p>Instead, humans learn by making <a rel=\"nofollow noopener\" target=\"_blank\" href=\"https:\/\/link.springer.com\/article\/10.1007\/s12559-014-9307-7\">structured mental concepts<\/a>, in which many different properties and associations are linked together. For instance, our concept of \u201cbanana\u201d includes its shape, the color yellow, knowledge of it being a fruit, how to hold it, and so forth.<\/p>\n<p>As far as we know, AI systems do not form conceptual knowledge like this. They rely entirely on extracting complex statistical associations from their training data, and then applying these to similar contexts.<\/p>\n<p>Efforts are underway to build AI that <a rel=\"nofollow noopener\" target=\"_blank\" href=\"https:\/\/www.techrepublic.com\/article\/multimodal-learning-the-future-of-artificial-intelligence\/\">combines different types of input<\/a> (such as images and text) \u2013 but it remains to be seen if this will be sufficient for these models to learn the same types of rich mental representations humans use to understand the world.<\/p>\n<p>There\u2019s still much we don\u2019t know about how humans learn, understand and reason. However, what we do know indicates humans perform these tasks very differently to AI systems.<\/p>\n<p>As such, <a rel=\"nofollow noopener\" target=\"_blank\" href=\"https:\/\/www.zdnet.com\/article\/resisting-the-urge-to-be-impressed-and-knowing-what-we-are-talking-about-when-we-talk-about-ai\/\">many researchers believe<\/a> we\u2019ll need new approaches, and more fundamental insight into how the human brain works, before we can build machines that truly think and learn like humans.<!-- Below is The Conversation's page counter tag. Please DO NOT REMOVE. --><img decoding=\"async\" loading=\"lazy\" style=\"border: none !important; box-shadow: none !important; margin: 0 !important; max-height: 1px !important; max-width: 1px !important; min-height: 1px !important; min-width: 1px !important; opacity: 0 !important; outline: none !important; padding: 0 !important;\" alt=\"The Conversation\" width=\"1\" height=\"1\" class=\"js-lazy\" src=\"https:\/\/counter.theconversation.com\/content\/183993\/count.gif?distributor=republish-lightbox-basic\"\/><!-- End of code. If you don't see any code above, please get new code from the Advanced tab after you click the republish button. The page counter does not collect any personal data. More info: https:\/\/theconversation.com\/republishing-guidelines --><\/p>\n<p><noscript><img decoding=\"async\" loading=\"lazy\" style=\"border: none !important; box-shadow: none !important; margin: 0 !important; max-height: 1px !important; max-width: 1px !important; min-height: 1px !important; min-width: 1px !important; opacity: 0 !important; outline: none !important; padding: 0 !important;\" src=\"https:\/\/counter.theconversation.com\/content\/183993\/count.gif?distributor=republish-lightbox-basic\" alt=\"The Conversation\" width=\"1\" height=\"1\" class=\"\" srcset=\"\"\/><\/noscript><br \/>\n<em>This article by <a rel=\"nofollow noopener\" target=\"_blank\" href=\"https:\/\/theconversation.com\/profiles\/james-fodor-1346077\">James Fodor<\/a>, PhD Candidate in Cognitive Neuro<a href=\"https:\/\/buradabiliyorum.com\/en\/category\/sciencee\/\" data-internallinksmanager029f6b8e52c=\"5\" title=\"Science\" target=\"_blank\" rel=\"noopener\">science<\/a>, <a rel=\"nofollow noopener\" target=\"_blank\" href=\"https:\/\/theconversation.com\/institutions\/the-university-of-melbourne-722\">The University of Melbourne<\/a>, is republished from <a rel=\"nofollow noopener\" target=\"_blank\" href=\"https:\/\/theconversation.com\">The Conversation<\/a> under a Creative Commons license. Read the <a rel=\"nofollow noopener\" target=\"_blank\" href=\"https:\/\/theconversation.com\/were-told-ai-neural-networks-learn-the-way-humans-do-a-neuroscientist-explains-why-thats-not-the-case-183993\">original article<\/a>.<\/em>\n                        <\/div>\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\/CAAqBwgKMLG0nwswvr63Aw\" 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;\">For forums sites go to <span style=\"color: #ff9900;\"><a style=\"color: #ff9900;\" href=\"https:\/\/forum.buradabiliyorum.com\/\" target=\"_blank\" rel=\"noopener\">Forum.BuradaBiliyorum.Com<\/a><\/span><\/strong>\n<\/p><\/blockquote>\n<blockquote>\n<p style=\"text-align: center;\"><strong>If you want to read more like this article, you can visit our <span style=\"color: #ff9900;\"><a style=\"color: #ff9900;\" href=\"https:\/\/en.buradabiliyorum.com\/technology\/\" target=\"_blank\" rel=\"noopener\">Technology category.<\/a><\/span><\/strong><\/p>\n<\/blockquote>\n<p><span style=\"color: black;\"><a style=\"color: #ff9900;\" href=\"https:\/\/thenextweb.com\/news\/neural-networks-dont-work-like-the-human-brain-because-they-learn-differently\" target=\"_blank\" rel=\"noopener\">Source<\/a><\/span><\/p>\n","protected":false},"excerpt":{"rendered":"<p>&#8220;How neural networks &#8216;learn&#8217; differently than the human brain&#8221; Recently developed artificial intelligence (AI) models are capable of many impressive feats, including recognizing images and producing human-like language. But just because AI can perform human-like behaviors doesn\u2019t mean it can think or understand like humans. As a researcher studying how humans understand and reason about&#8230;<\/p>\n","protected":false},"author":1,"featured_media":458513,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"fifu_image_url":"https:\/\/img-cdn.tnwcdn.com\/image\/neural?filter_last=1&fit=1280,640&url=https:\/\/cdn0.tnwcdn.com\/wp-content\/blogs.dir\/1\/files\/2022\/06\/Neural-networks.jpg&signature=866573870d7612f577731d80bee1a544","fifu_image_alt":"","footnotes":""},"categories":[18],"tags":[],"class_list":["post-458512","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-technology"],"_links":{"self":[{"href":"https:\/\/buradabiliyorum.com\/en\/wp-json\/wp\/v2\/posts\/458512","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=458512"}],"version-history":[{"count":0,"href":"https:\/\/buradabiliyorum.com\/en\/wp-json\/wp\/v2\/posts\/458512\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/buradabiliyorum.com\/en\/wp-json\/wp\/v2\/media\/458513"}],"wp:attachment":[{"href":"https:\/\/buradabiliyorum.com\/en\/wp-json\/wp\/v2\/media?parent=458512"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/buradabiliyorum.com\/en\/wp-json\/wp\/v2\/categories?post=458512"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/buradabiliyorum.com\/en\/wp-json\/wp\/v2\/tags?post=458512"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}