{"id":256796,"date":"2021-05-23T10:44:54","date_gmt":"2021-05-23T07:44:54","guid":{"rendered":"https:\/\/en.buradabiliyorum.com\/whats-the-difference-between-human-eyes-and-computer-vision\/"},"modified":"2021-05-23T10:44:54","modified_gmt":"2021-05-23T07:44:54","slug":"whats-the-difference-between-human-eyes-and-computer-vision","status":"publish","type":"post","link":"https:\/\/buradabiliyorum.com\/en\/whats-the-difference-between-human-eyes-and-computer-vision\/","title":{"rendered":"#What\u2019s the difference between human eyes and computer vision?"},"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-6a357eca06492\" 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-6a357eca06492\" 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\/whats-the-difference-between-human-eyes-and-computer-vision\/#Hardware_differences\" >Hardware differences<\/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\/whats-the-difference-between-human-eyes-and-computer-vision\/#Architecture_differences\" >Architecture differences<\/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\/whats-the-difference-between-human-eyes-and-computer-vision\/#Goal_differences\" >Goal differences<\/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\/whats-the-difference-between-human-eyes-and-computer-vision\/#Integration_differences\" >Integration differences<\/a><\/li><\/ul><\/nav><\/div>\n<p>&#8220;<strong>#What\u2019s the difference between human eyes and computer vision?<\/strong>&#8221;<\/p>\n<div>Since the early years of artificial intelligence, scientists have dreamed of creating computers that can \u201csee\u201d the world. As vision plays a key role in many things we do every day, cracking the code of<span>\u00a0<\/span><a rel=\"nofollow noopener\" target=\"_blank\" href=\"https:\/\/bdtechtalks.com\/2019\/01\/14\/what-is-computer-vision\/\">computer vision<\/a><span>\u00a0<\/span>seemed to be one of the major steps toward developing artificial <a href=\"https:\/\/buradabiliyorum.com\/en\/category\/general\/\" data-internallinksmanager029f6b8e52c=\"3\" title=\"General\" target=\"_blank\" rel=\"noopener\">general<\/a> intelligence.<\/p>\n<p>But like many other goals in AI, computer vision has proven to be easier said than done. In 1966, scientists at MIT launched \u201c<a rel=\"nofollow noopener\" target=\"_blank\" href=\"http:\/\/people.csail.mit.edu\/brooks\/idocs\/AIM-100.pdf\">The Summer Vision Project<\/a>,\u201d a two-month effort to create a computer system that could identify objects and background areas in images. But it took much more than a summer break to achieve those goals. In fact, it wasn\u2019t until the early 2010s that image classifiers and object detectors were flexible and reliable enough to be used in mainstream <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>lications.<\/p>\n<p>In the past decades, advances in<span>\u00a0<\/span><a rel=\"nofollow noopener\" target=\"_blank\" href=\"https:\/\/bdtechtalks.com\/2017\/08\/28\/artificial-intelligence-machine-learning-deep-learning\/\">machine learning<\/a><span>\u00a0<\/span>and neuro<a href=\"https:\/\/buradabiliyorum.com\/en\/category\/sciencee\/\" data-internallinksmanager029f6b8e52c=\"5\" title=\"Science\" target=\"_blank\" rel=\"noopener\">science<\/a> have helped make great strides in computer vision. But we still have a long way to go before we can build AI systems that see the world as we do.<\/p>\n<p><a rel=\"nofollow noopener\" target=\"_blank\" href=\"https:\/\/www.cambridge.org\/core\/books\/biological-and-computer-vision\/BB7E68A69AFE7A322F68F3C4A297F3CF\"><em>Biological and Computer Vision<\/em><\/a>, a book by Harvard Medical University Professor Gabriel Kreiman, provides an accessible account of how humans and animals process visual data and how far we\u2019ve come toward replicating these functions in computers.<\/p>\n<p>Kreiman\u2019s book helps understand the differences between biological and computer vision. The book details how billions of years of evolution have equipped us with a complicated visual processing system, and how studying it has helped inspire better computer vision algorithms. Kreiman also discusses what separates contemporary computer vision systems from their biological counterpart.<\/p>\n<p>While I would recommend a full read of<span>\u00a0<\/span><em>Biological and Computer Vision<\/em>\u00a0to anyone who is interested in the field, I\u2019ve tried here (with some help from Gabriel himself) to lay out some of my key takeaways from the book.<\/p>\n<h2><span class=\"ez-toc-section\" id=\"Hardware_differences\"><\/span>Hardware differences<span class=\"ez-toc-section-end\"><\/span><\/h2>\n<div class=\"wp-block-image\">\n<figure class=\"aligncenter size-large\"><a rel=\"nofollow noopener\" target=\"_blank\" href=\"https:\/\/i0.wp.com\/bdtechtalks.com\/wp-content\/uploads\/2021\/05\/brain-vs-integrated-circuits.jpg?ssl=1\"><\/p>\n<figure class=\"post-image post-mediaBleed aligncenter\"><img loading=\"lazy\" decoding=\"async\" class=\"wp-image-10286 jetpack-js-lazy-image jetpack-js-lazy-image--handled aligncenter js-lazy\" sizes=\"auto, (max-width: 696px) 100vw, 696px\" alt=\"brain vs integrated circuits\" width=\"696\" height=\"392\" data-attachment-id=\"10286\" data-permalink=\"https:\/\/bdtechtalks.com\/2021\/05\/10\/biological-computer-vision\/brain-vs-integrated-circuits\/\" data-orig-file=\"https:\/\/i0.wp.com\/bdtechtalks.com\/wp-content\/uploads\/2021\/05\/brain-vs-integrated-circuits.jpg?fit=1920%2C1080&amp;ssl=1\" data-orig-size=\"1920,1080\" data-comments-opened=\"1\" data-image-meta=\"{\" aperture=\"\" data-image-title=\"brain vs integrated circuits\" data-image-description=\"\" data-medium-file=\"https:\/\/i0.wp.com\/bdtechtalks.com\/wp-content\/uploads\/2021\/05\/brain-vs-integrated-circuits.jpg?fit=300%2C169&amp;ssl=1\" data-large-file=\"https:\/\/i0.wp.com\/bdtechtalks.com\/wp-content\/uploads\/2021\/05\/brain-vs-integrated-circuits.jpg?fit=696%2C392&amp;ssl=1\" data-recalc-dims=\"1\" data-lazy-loaded=\"1\" src=\"https:\/\/i0.wp.com\/bdtechtalks.com\/wp-content\/uploads\/2021\/05\/brain-vs-integrated-circuits.jpg?resize=696%2C392&amp;ssl=1\" srcset=\"https:\/\/i0.wp.com\/bdtechtalks.com\/wp-content\/uploads\/2021\/05\/brain-vs-integrated-circuits.jpg?resize=1024%2C576&amp;ssl=1 1024w, https:\/\/i0.wp.com\/bdtechtalks.com\/wp-content\/uploads\/2021\/05\/brain-vs-integrated-circuits.jpg?resize=300%2C169&amp;ssl=1 300w, https:\/\/i0.wp.com\/bdtechtalks.com\/wp-content\/uploads\/2021\/05\/brain-vs-integrated-circuits.jpg?resize=768%2C432&amp;ssl=1 768w, https:\/\/i0.wp.com\/bdtechtalks.com\/wp-content\/uploads\/2021\/05\/brain-vs-integrated-circuits.jpg?resize=1536%2C864&amp;ssl=1 1536w, https:\/\/i0.wp.com\/bdtechtalks.com\/wp-content\/uploads\/2021\/05\/brain-vs-integrated-circuits.jpg?resize=696%2C392&amp;ssl=1 696w, https:\/\/i0.wp.com\/bdtechtalks.com\/wp-content\/uploads\/2021\/05\/brain-vs-integrated-circuits.jpg?resize=1068%2C601&amp;ssl=1 1068w, https:\/\/i0.wp.com\/bdtechtalks.com\/wp-content\/uploads\/2021\/05\/brain-vs-integrated-circuits.jpg?resize=747%2C420&amp;ssl=1 747w, https:\/\/i0.wp.com\/bdtechtalks.com\/wp-content\/uploads\/2021\/05\/brain-vs-integrated-circuits.jpg?w=1920&amp;ssl=1 1920w, https:\/\/i0.wp.com\/bdtechtalks.com\/wp-content\/uploads\/2021\/05\/brain-vs-integrated-circuits.jpg?w=1392&amp;ssl=1 1392w\"\/><noscript><img loading=\"lazy\" decoding=\"async\" class=\"wp-image-10286 jetpack--image jetpack--image--handled aligncenter\" src=\"https:\/\/i0.wp.com\/bdtechtalks.com\/wp-content\/uploads\/2021\/05\/brain-vs-integrated-circuits.jpg?resize=696%2C392&amp;ssl=1\" alt=\"brain vs integrated circuits\" width=\"696\" height=\"392\" data-attachment-id=\"10286\" data-permalink=\"https:\/\/bdtechtalks.com\/2021\/05\/10\/biological-computer-vision\/brain-vs-integrated-circuits\/\" data-orig-file=\"https:\/\/i0.wp.com\/bdtechtalks.com\/wp-content\/uploads\/2021\/05\/brain-vs-integrated-circuits.jpg?fit=1920%2C1080&amp;ssl=1\" data-orig-size=\"1920,1080\" data-comments-opened=\"1\" data-image-meta=\"{\" aperture=\"\" data-image-title=\"brain vs integrated circuits\" data-image-description=\"\" data-medium-file=\"https:\/\/i0.wp.com\/bdtechtalks.com\/wp-content\/uploads\/2021\/05\/brain-vs-integrated-circuits.jpg?fit=300%2C169&amp;ssl=1\" data-large-file=\"https:\/\/i0.wp.com\/bdtechtalks.com\/wp-content\/uploads\/2021\/05\/brain-vs-integrated-circuits.jpg?fit=696%2C392&amp;ssl=1\" data-recalc-dims=\"1\" data-lazy-loaded=\"1\" srcset=\"https:\/\/i0.wp.com\/bdtechtalks.com\/wp-content\/uploads\/2021\/05\/brain-vs-integrated-circuits.jpg?resize=1024%2C576&amp;ssl=1 1024w, https:\/\/i0.wp.com\/bdtechtalks.com\/wp-content\/uploads\/2021\/05\/brain-vs-integrated-circuits.jpg?resize=300%2C169&amp;ssl=1 300w, https:\/\/i0.wp.com\/bdtechtalks.com\/wp-content\/uploads\/2021\/05\/brain-vs-integrated-circuits.jpg?resize=768%2C432&amp;ssl=1 768w, https:\/\/i0.wp.com\/bdtechtalks.com\/wp-content\/uploads\/2021\/05\/brain-vs-integrated-circuits.jpg?resize=1536%2C864&amp;ssl=1 1536w, https:\/\/i0.wp.com\/bdtechtalks.com\/wp-content\/uploads\/2021\/05\/brain-vs-integrated-circuits.jpg?resize=696%2C392&amp;ssl=1 696w, https:\/\/i0.wp.com\/bdtechtalks.com\/wp-content\/uploads\/2021\/05\/brain-vs-integrated-circuits.jpg?resize=1068%2C601&amp;ssl=1 1068w, https:\/\/i0.wp.com\/bdtechtalks.com\/wp-content\/uploads\/2021\/05\/brain-vs-integrated-circuits.jpg?resize=747%2C420&amp;ssl=1 747w, https:\/\/i0.wp.com\/bdtechtalks.com\/wp-content\/uploads\/2021\/05\/brain-vs-integrated-circuits.jpg?w=1920&amp;ssl=1 1920w, https:\/\/i0.wp.com\/bdtechtalks.com\/wp-content\/uploads\/2021\/05\/brain-vs-integrated-circuits.jpg?w=1392&amp;ssl=1 1392w\"\/><\/noscript><\/figure>\n<p><\/a><figcaption\/><\/figure>\n<\/div>\n<p>In the introduction to<span>\u00a0<\/span><em>Biological and Computer Vision<\/em>, Kreiman writes, \u201cI am particularly excited about connecting biological and computational circuits. Biological vision is the product of millions of years of evolution. There is no reason to reinvent the wheel when developing computational models. We can learn from how biology solves vision problems and use the solutions as inspiration to build better algorithms.\u201d<\/p>\n<p>And indeed, the study of the visual cortex has been<span>\u00a0<\/span><a rel=\"nofollow noopener\" target=\"_blank\" href=\"https:\/\/bdtechtalks.com\/2020\/01\/20\/neuroscience-artificial-intelligence-synergies\/\">a great source of inspiration for computer vision and AI<\/a>. But before being able to digitize vision, scientists had to overcome the huge hardware gap between biological and computer vision. Biological vision runs on an interconnected network of cortical cells and organic neurons. Computer vision, on the other hand, runs on electronic chips composed of transistors.<\/p>\n<p>Therefore, a theory of vision must be defined at a level that can be implemented in computers in a way that is comparable to living beings. Kreiman calls this the \u201cGoldilocks resolution,\u201d a level of abstraction that is neither too detailed nor too simplified.<\/p>\n<p>For instance, early efforts in computer vision tried to tackle computer vision at a very abstract level, in a way that ignored how human and animal brains recognize visual patterns. Those approaches have proven to be very brittle and inefficient. On the other hand, studying and simulating brains at the molecular level would prove to be computationally inefficient.<\/p>\n<p>\u201cI am not a big fan of what I call \u2018copying biology,\u2019\u201d Kreiman told<span>\u00a0<\/span><em>TechTalks<\/em>. \u201cThere are many aspects of biology that can and should be abstracted away. We probably do not need units with 20,000 proteins and a cytoplasm and complex dendritic geometries. That would be too much biological detail. On the other hand, we cannot merely study behavior\u2014that is not enough detail.\u201d<\/p>\n<p>In<span>\u00a0<\/span><em>Biological and Computer Vision,<span>\u00a0<\/span><\/em>Kreiman defines the Goldilocks scale of neocortical circuits as neuronal activities per millisecond. Advances in neuroscience and medical <a href=\"https:\/\/buradabiliyorum.com\/en\/category\/technology\/\" data-internallinksmanager029f6b8e52c=\"4\" title=\"Technology\" target=\"_blank\" rel=\"noopener\">technology<\/a> have made it possible to study the activities of individual neurons at millisecond time granularity.<\/p>\n<p>And the results of those studies have helped develop different types of<span>\u00a0<\/span><a rel=\"nofollow noopener\" target=\"_blank\" href=\"https:\/\/bdtechtalks.com\/2019\/08\/05\/what-is-artificial-neural-network-ann\/\">artificial neural networks<\/a>, AI algorithms that loosely simulate the workings of cortical areas of the mammal brain. In recent years, neural networks have proven to be the most efficient algorithm for pattern recognition in visual data and have become the key component of many<span>\u00a0<\/span><a rel=\"nofollow noopener\" target=\"_blank\" href=\"https:\/\/bdtechtalks.com\/2019\/12\/30\/computer-vision-applications-deep-learning\/\">computer vision applications<\/a>.<\/p>\n<h2><span class=\"ez-toc-section\" id=\"Architecture_differences\"><\/span>Architecture differences<span class=\"ez-toc-section-end\"><\/span><\/h2>\n<p>The recent decades have seen a slew of innovative work in the field of<span>\u00a0<\/span><a rel=\"nofollow noopener\" target=\"_blank\" href=\"https:\/\/bdtechtalks.com\/2021\/01\/28\/deep-learning-explainer\/\">deep learning<\/a>, which has helped computers mimic some of the functions of biological vision.<span>\u00a0<\/span><a rel=\"nofollow noopener\" target=\"_blank\" href=\"https:\/\/bdtechtalks.com\/2020\/01\/06\/convolutional-neural-networks-cnn-convnets\/\">Convolutional layers<\/a>, inspired by studies made on the animal visual cortex, are very efficient at finding patterns in visual data. Pooling layers help generalize the output of a convolutional layer and make it less sensitive to the displacement of visual patterns. Stacked on top of each other, blocks of convolutional and pooling layers can go from finding small patterns (corners, edges, etc.) to complex objects (faces, chairs, cars, etc.).<\/p>\n<p>But there\u2019s still a mismatch between the high-level architecture of artificial neural networks and what we know about the mammal visual cortex.<\/p>\n<p>\u201cThe word \u2018layers\u2019 is, unfortunately, a bit ambiguous,\u201d Kreiman said. \u201cIn computer science, people use layers to connote the different processing stages (and a layer is mostly analogous to a brain area). In biology, each brain region contains six cortical layers (and subdivisions). My hunch is that six-layer structure (the connectivity of which is sometimes referred to as a canonical microcircuit) is quite crucial. It remains unclear what aspects of this circuitry should we include in neural networks. Some may argue that aspects of the six-layer motif are already incorporated (e.g. normalization operations). But there is probably enormous richness missing.\u201d<\/p>\n<p>Also, as Kreiman highlights in<span>\u00a0<\/span><em>Biological and Computer Vision<\/em>, information in the brain moves in several directions. Light signals move from the retina to the inferior temporal cortex to the V1, V2, and other layers of the visual cortex. But each layer also provides feedback to its predecessors. And within each layer, neurons interact and pass information between each other. All these interactions and interconnections help the brain fill in the gaps in visual input and make inferences when it has incomplete information.<\/p>\n<p>In contrast, in artificial neural networks, data usually moves in a single direction. Convolutional neural networks are \u201cfeedforward networks,\u201d which means information only goes from the input layer to the higher and output layers.<\/p>\n<p>There\u2019s a feedback mechanism called \u201cbackpropagation,\u201d which helps correct mistakes and tune the parameters of neural networks. But backpropagation is computationally expensive and only used during the training of neural networks. And it\u2019s not clear if backpropagation directly corresponds to the feedback mechanisms of cortical layers.<\/p>\n<p>On the other hand,<span>\u00a0<\/span><a rel=\"nofollow noopener\" target=\"_blank\" href=\"https:\/\/bdtechtalks.com\/2020\/06\/08\/what-is-recurrent-neural-network-rnn\/\">recurrent neural networks<\/a>, which combine the output of higher layers into the input of their previous layers, still have limited use in computer vision.<\/p>\n<div class=\"wp-block-image\">\n<figure class=\"aligncenter size-large\">\n<p><figure class=\"post-image post-mediaBleed aligncenter\"><a rel=\"nofollow noopener\" target=\"_blank\" href=\"https:\/\/i2.wp.com\/bdtechtalks.com\/wp-content\/uploads\/2021\/05\/visual-cortex-vs-neural-networks.jpg?ssl=1\"><img loading=\"lazy\" decoding=\"async\" class=\"jetpack-js-lazy-image jetpack-js-lazy-image--handled wp-image-10288 js-lazy\" sizes=\"auto, (max-width: 696px) 100vw, 696px\" alt=\"visual cortex vs neural networks\" width=\"696\" height=\"392\" data-attachment-id=\"10288\" data-permalink=\"https:\/\/bdtechtalks.com\/2021\/05\/10\/biological-computer-vision\/visual-cortex-vs-neural-networks\/\" data-orig-file=\"https:\/\/i2.wp.com\/bdtechtalks.com\/wp-content\/uploads\/2021\/05\/visual-cortex-vs-neural-networks.jpg?fit=1920%2C1080&amp;ssl=1\" data-orig-size=\"1920,1080\" data-comments-opened=\"1\" data-image-meta=\"{\" aperture=\"\" data-image-title=\"visual cortex vs neural networks\" data-image-description=\"\" data-medium-file=\"https:\/\/i2.wp.com\/bdtechtalks.com\/wp-content\/uploads\/2021\/05\/visual-cortex-vs-neural-networks.jpg?fit=300%2C169&amp;ssl=1\" data-large-file=\"https:\/\/i2.wp.com\/bdtechtalks.com\/wp-content\/uploads\/2021\/05\/visual-cortex-vs-neural-networks.jpg?fit=696%2C392&amp;ssl=1\" data-recalc-dims=\"1\" data-lazy-loaded=\"1\" src=\"https:\/\/i2.wp.com\/bdtechtalks.com\/wp-content\/uploads\/2021\/05\/visual-cortex-vs-neural-networks.jpg?resize=696%2C392&amp;ssl=1\" srcset=\"https:\/\/i2.wp.com\/bdtechtalks.com\/wp-content\/uploads\/2021\/05\/visual-cortex-vs-neural-networks.jpg?resize=1024%2C576&amp;ssl=1 1024w, https:\/\/i2.wp.com\/bdtechtalks.com\/wp-content\/uploads\/2021\/05\/visual-cortex-vs-neural-networks.jpg?resize=300%2C169&amp;ssl=1 300w, https:\/\/i2.wp.com\/bdtechtalks.com\/wp-content\/uploads\/2021\/05\/visual-cortex-vs-neural-networks.jpg?resize=768%2C432&amp;ssl=1 768w, https:\/\/i2.wp.com\/bdtechtalks.com\/wp-content\/uploads\/2021\/05\/visual-cortex-vs-neural-networks.jpg?resize=1536%2C864&amp;ssl=1 1536w, https:\/\/i2.wp.com\/bdtechtalks.com\/wp-content\/uploads\/2021\/05\/visual-cortex-vs-neural-networks.jpg?resize=696%2C392&amp;ssl=1 696w, https:\/\/i2.wp.com\/bdtechtalks.com\/wp-content\/uploads\/2021\/05\/visual-cortex-vs-neural-networks.jpg?resize=1068%2C601&amp;ssl=1 1068w, https:\/\/i2.wp.com\/bdtechtalks.com\/wp-content\/uploads\/2021\/05\/visual-cortex-vs-neural-networks.jpg?resize=747%2C420&amp;ssl=1 747w, https:\/\/i2.wp.com\/bdtechtalks.com\/wp-content\/uploads\/2021\/05\/visual-cortex-vs-neural-networks.jpg?w=1920&amp;ssl=1 1920w, https:\/\/i2.wp.com\/bdtechtalks.com\/wp-content\/uploads\/2021\/05\/visual-cortex-vs-neural-networks.jpg?w=1392&amp;ssl=1 1392w\"\/><noscript><img loading=\"lazy\" decoding=\"async\" class=\"jetpack--image jetpack--image--handled wp-image-10288\" src=\"https:\/\/i2.wp.com\/bdtechtalks.com\/wp-content\/uploads\/2021\/05\/visual-cortex-vs-neural-networks.jpg?resize=696%2C392&amp;ssl=1\" alt=\"visual cortex vs neural networks\" width=\"696\" height=\"392\" data-attachment-id=\"10288\" data-permalink=\"https:\/\/bdtechtalks.com\/2021\/05\/10\/biological-computer-vision\/visual-cortex-vs-neural-networks\/\" data-orig-file=\"https:\/\/i2.wp.com\/bdtechtalks.com\/wp-content\/uploads\/2021\/05\/visual-cortex-vs-neural-networks.jpg?fit=1920%2C1080&amp;ssl=1\" data-orig-size=\"1920,1080\" data-comments-opened=\"1\" data-image-meta=\"{\" aperture=\"\" data-image-title=\"visual cortex vs neural networks\" data-image-description=\"\" data-medium-file=\"https:\/\/i2.wp.com\/bdtechtalks.com\/wp-content\/uploads\/2021\/05\/visual-cortex-vs-neural-networks.jpg?fit=300%2C169&amp;ssl=1\" data-large-file=\"https:\/\/i2.wp.com\/bdtechtalks.com\/wp-content\/uploads\/2021\/05\/visual-cortex-vs-neural-networks.jpg?fit=696%2C392&amp;ssl=1\" data-recalc-dims=\"1\" data-lazy-loaded=\"1\" srcset=\"https:\/\/i2.wp.com\/bdtechtalks.com\/wp-content\/uploads\/2021\/05\/visual-cortex-vs-neural-networks.jpg?resize=1024%2C576&amp;ssl=1 1024w, https:\/\/i2.wp.com\/bdtechtalks.com\/wp-content\/uploads\/2021\/05\/visual-cortex-vs-neural-networks.jpg?resize=300%2C169&amp;ssl=1 300w, https:\/\/i2.wp.com\/bdtechtalks.com\/wp-content\/uploads\/2021\/05\/visual-cortex-vs-neural-networks.jpg?resize=768%2C432&amp;ssl=1 768w, https:\/\/i2.wp.com\/bdtechtalks.com\/wp-content\/uploads\/2021\/05\/visual-cortex-vs-neural-networks.jpg?resize=1536%2C864&amp;ssl=1 1536w, https:\/\/i2.wp.com\/bdtechtalks.com\/wp-content\/uploads\/2021\/05\/visual-cortex-vs-neural-networks.jpg?resize=696%2C392&amp;ssl=1 696w, https:\/\/i2.wp.com\/bdtechtalks.com\/wp-content\/uploads\/2021\/05\/visual-cortex-vs-neural-networks.jpg?resize=1068%2C601&amp;ssl=1 1068w, https:\/\/i2.wp.com\/bdtechtalks.com\/wp-content\/uploads\/2021\/05\/visual-cortex-vs-neural-networks.jpg?resize=747%2C420&amp;ssl=1 747w, https:\/\/i2.wp.com\/bdtechtalks.com\/wp-content\/uploads\/2021\/05\/visual-cortex-vs-neural-networks.jpg?w=1920&amp;ssl=1 1920w, https:\/\/i2.wp.com\/bdtechtalks.com\/wp-content\/uploads\/2021\/05\/visual-cortex-vs-neural-networks.jpg?w=1392&amp;ssl=1 1392w\"\/><\/noscript><\/a><figcaption><a rel=\"nofollow noopener\" target=\"_blank\" href=\"https:\/\/thenextweb.com\/news\/#\" data-url=\"https:\/\/twitter.com\/intent\/tweet?url=https%3A%2F%2Feditorial.thenextweb.com%2Fneural%2F2021%2F05%2F23%2Fwhats-the-difference-between-human-eyes-and-computer-vision%2F&amp;via=thenextweb&amp;related=thenextweb&amp;text=Check out this picture on: In the visual cortex (right), information moves in several directions. In neural networks (left), information moves in one direction.\" data-title=\"Share In the visual cortex (right), information moves in several directions. In neural networks (left), information moves in one direction. on Twitter\" data-width=\"685\" data-height=\"500\" class=\"post-image-share popitup\" title=\"Share In the visual cortex (right), information moves in several directions. In neural networks (left), information moves in one direction. on Twitter\"><i class=\"icon icon--inline icon--twitter--dark\"\/><\/a>In the visual cortex (right), information moves in several directions. In neural networks (left), information moves in one direction.<\/figcaption><\/figure><figcaption\/><\/p>\n<\/figure>\n<\/div>\n<p>In our conversation, Kreiman suggested that lateral and top-down flow of information can be crucial to bringing artificial neural networks to their biological counterparts.<\/p>\n<p>\u201cHorizontal connections (i.e., connections for units within a layer) may be critical for certain computations such as pattern completion,\u201d he said. \u201cTop-down connections (i.e., connections from units in a layer to units in a layer below) are probably essential to make predictions, for attention, to incorporate contextual information, etc.\u201d<\/p>\n<p>He also said out that neurons have \u201ccomplex temporal integrative properties that are missing in current networks.\u201d<\/p>\n<h2><span class=\"ez-toc-section\" id=\"Goal_differences\"><\/span>Goal differences<span class=\"ez-toc-section-end\"><\/span><\/h2>\n<p>Evolution has managed to develop a neural architecture that can accomplish many tasks. Several studies have shown that our visual system\u00a0<a rel=\"nofollow noopener\" target=\"_blank\" href=\"https:\/\/bdtechtalks.com\/2020\/06\/01\/artificial-intelligence-computer-vision-fpicu\/\">can dynamically tune its sensitivities to the goals<\/a><span>\u00a0<\/span>we want to accomplish. Creating computer vision systems that have this kind of flexibility remains a major challenge, however.<\/p>\n<p>Current computer vision systems are designed to accomplish a single task. We have neural networks that can classify objects, localize objects, segment images into different objects, describe images, generate images, and more. But each neural network can accomplish a single task alone.<\/p>\n<figure class=\"alignleft size-large is-resized\"><figcaption>Harvard Medical University professor Gabriel Kreiman. Author of \u201cBiological and Computer Vision. \u201cA central issue is to understand \u2018visual routines,\u2019 a term coined by Shimon Ullman; how can we flexibly route visual information in a task-dependent manner?\u201d Kreiman said. \u201cYou can essentially answer an infinite number of questions on an image. You don\u2019t just label objects, you can count objects, you can describe their colors, their interactions, their sizes, etc. We can build networks to do each of these things, but we do not have networks that can do all of these things simultaneously. There are interesting approaches to this via question\/answering systems, but these algorithms, exciting as they are, remain rather primitive, especially in comparison with human performance.\u201d<\/figcaption><\/figure>\n<\/p>\n<h2><span class=\"ez-toc-section\" id=\"Integration_differences\"><\/span>Integration differences<span class=\"ez-toc-section-end\"><\/span><\/h2>\n<p>In humans and animals, vision is closely related to smell, touch, and hearing senses. The visual, auditory, somatosensory, and olfactory cortices interact and pick up cues from each other to adjust their inferences of the world. In AI systems, on the other hand, each of these things exists separately.<\/p>\n<p>Do we need this kind of integration to make better computer vision systems?<\/p>\n<p>\u201cAs scientists, we often like to divide problems to conquer them,\u201d Kreiman said. \u201cI personally think that this is a reasonable way to start. We can see very well without smell or hearing. Consider a Chaplin movie (and remove all the minimal music and text). You can understand a<span>\u00a0<\/span><em>lot<\/em>. If a person is born deaf, they can still see very well. Sure, there are lots of examples of interesting interactions across modalities, but mostly I think that we will make lots of progress with this simplification.\u201d<\/p>\n<p>However, a more complicated matter is the integration of vision with more complex areas of the brain. In humans, vision is deeply integrated with other brain functions such as logic, reasoning, language, and common sense knowledge.<\/p>\n<p>\u201cSome (most?) visual problems may \u2018cost\u2019 more time and require integrating visual inputs with existing knowledge about the world,\u201d Kreiman said.<\/p>\n<p>He pointed to following picture of former U.S. president Barack Obama as an example.<\/p>\n<div class=\"wp-block-image\">\n<figure class=\"aligncenter size-large\">\n<p><figure class=\"post-image post-mediaBleed aligncenter\"><a rel=\"nofollow noopener\" target=\"_blank\" href=\"https:\/\/i0.wp.com\/bdtechtalks.com\/wp-content\/uploads\/2021\/05\/ObamaPicture.jpg?ssl=1\"><img loading=\"lazy\" decoding=\"async\" class=\"jetpack-js-lazy-image jetpack-js-lazy-image--handled wp-image-10293 js-lazy\" sizes=\"auto, (max-width: 638px) 100vw, 638px\" alt=\"Obama Picture\" width=\"638\" height=\"441\" data-attachment-id=\"10293\" data-permalink=\"https:\/\/bdtechtalks.com\/2021\/05\/10\/biological-computer-vision\/obamapicture\/\" data-orig-file=\"https:\/\/i0.wp.com\/bdtechtalks.com\/wp-content\/uploads\/2021\/05\/ObamaPicture.jpg?fit=638%2C441&amp;ssl=1\" data-orig-size=\"638,441\" data-comments-opened=\"1\" data-image-meta=\"{\" aperture=\"\" data-image-title=\"Obama Picture\" data-image-description=\"\" data-medium-file=\"https:\/\/i0.wp.com\/bdtechtalks.com\/wp-content\/uploads\/2021\/05\/ObamaPicture.jpg?fit=300%2C207&amp;ssl=1\" data-large-file=\"https:\/\/i0.wp.com\/bdtechtalks.com\/wp-content\/uploads\/2021\/05\/ObamaPicture.jpg?fit=638%2C441&amp;ssl=1\" data-recalc-dims=\"1\" data-lazy-loaded=\"1\" src=\"https:\/\/i0.wp.com\/bdtechtalks.com\/wp-content\/uploads\/2021\/05\/ObamaPicture.jpg?resize=638%2C441&amp;ssl=1\" srcset=\"https:\/\/i0.wp.com\/bdtechtalks.com\/wp-content\/uploads\/2021\/05\/ObamaPicture.jpg?w=638&amp;ssl=1 638w, https:\/\/i0.wp.com\/bdtechtalks.com\/wp-content\/uploads\/2021\/05\/ObamaPicture.jpg?resize=300%2C207&amp;ssl=1 300w, https:\/\/i0.wp.com\/bdtechtalks.com\/wp-content\/uploads\/2021\/05\/ObamaPicture.jpg?resize=100%2C70&amp;ssl=1 100w, https:\/\/i0.wp.com\/bdtechtalks.com\/wp-content\/uploads\/2021\/05\/ObamaPicture.jpg?resize=218%2C150&amp;ssl=1 218w, https:\/\/i0.wp.com\/bdtechtalks.com\/wp-content\/uploads\/2021\/05\/ObamaPicture.jpg?resize=608%2C420&amp;ssl=1 608w\"\/><noscript><img loading=\"lazy\" decoding=\"async\" class=\"jetpack--image jetpack--image--handled wp-image-10293\" src=\"https:\/\/i0.wp.com\/bdtechtalks.com\/wp-content\/uploads\/2021\/05\/ObamaPicture.jpg?resize=638%2C441&amp;ssl=1\" alt=\"Obama Picture\" width=\"638\" height=\"441\" data-attachment-id=\"10293\" data-permalink=\"https:\/\/bdtechtalks.com\/2021\/05\/10\/biological-computer-vision\/obamapicture\/\" data-orig-file=\"https:\/\/i0.wp.com\/bdtechtalks.com\/wp-content\/uploads\/2021\/05\/ObamaPicture.jpg?fit=638%2C441&amp;ssl=1\" data-orig-size=\"638,441\" data-comments-opened=\"1\" data-image-meta=\"{\" aperture=\"\" data-image-title=\"Obama Picture\" data-image-description=\"\" data-medium-file=\"https:\/\/i0.wp.com\/bdtechtalks.com\/wp-content\/uploads\/2021\/05\/ObamaPicture.jpg?fit=300%2C207&amp;ssl=1\" data-large-file=\"https:\/\/i0.wp.com\/bdtechtalks.com\/wp-content\/uploads\/2021\/05\/ObamaPicture.jpg?fit=638%2C441&amp;ssl=1\" data-recalc-dims=\"1\" data-lazy-loaded=\"1\" srcset=\"https:\/\/i0.wp.com\/bdtechtalks.com\/wp-content\/uploads\/2021\/05\/ObamaPicture.jpg?w=638&amp;ssl=1 638w, https:\/\/i0.wp.com\/bdtechtalks.com\/wp-content\/uploads\/2021\/05\/ObamaPicture.jpg?resize=300%2C207&amp;ssl=1 300w, https:\/\/i0.wp.com\/bdtechtalks.com\/wp-content\/uploads\/2021\/05\/ObamaPicture.jpg?resize=100%2C70&amp;ssl=1 100w, https:\/\/i0.wp.com\/bdtechtalks.com\/wp-content\/uploads\/2021\/05\/ObamaPicture.jpg?resize=218%2C150&amp;ssl=1 218w, https:\/\/i0.wp.com\/bdtechtalks.com\/wp-content\/uploads\/2021\/05\/ObamaPicture.jpg?resize=608%2C420&amp;ssl=1 608w\"\/><\/noscript><\/a><figcaption><a rel=\"nofollow noopener\" target=\"_blank\" href=\"https:\/\/thenextweb.com\/news\/#\" data-url=\"https:\/\/twitter.com\/intent\/tweet?url=https%3A%2F%2Feditorial.thenextweb.com%2Fneural%2F2021%2F05%2F23%2Fwhats-the-difference-between-human-eyes-and-computer-vision%2F&amp;via=thenextweb&amp;related=thenextweb&amp;text=Check out this picture on: Understanding what is going on it this picture requires world knowledge, social knowledge, and common sense.\" data-title=\"Share Understanding what is going on it this picture requires world knowledge, social knowledge, and common sense. on Twitter\" data-width=\"685\" data-height=\"500\" class=\"post-image-share popitup\" title=\"Share Understanding what is going on it this picture requires world knowledge, social knowledge, and common sense. on Twitter\"><i class=\"icon icon--inline icon--twitter--dark\"\/><\/a>Understanding what is going on it this picture requires world knowledge, <a href=\"https:\/\/buradabiliyorum.com\/en\/category\/social-mediaa\/\" data-internallinksmanager029f6b8e52c=\"1\" title=\"Social Media\" target=\"_blank\" rel=\"noopener\">social<\/a> knowledge, and common sense.<\/figcaption><\/figure><figcaption>\nTo understand what is going on in this picture, an AI agent would need to know what the person on the scale is doing, what Obama is doing, who is laughing and why they are laughing, etc. Answering these questions requires a wealth of information, including world knowledge (scales measure weight), physics knowledge (a foot on a scale exerts a force), psychological knowledge (many people are self-conscious about their weight and would be surprised if their weight is well above the usual), social understanding (some people are in on the joke, some are not).<\/figcaption><\/p>\n<\/figure>\n<\/div>\n<p>\u201cNo current architecture can do this. All of this will require dynamics (we do not appreciate all of this immediately and usually use many fixations to understand the image) and integration of top-down signals,\u201d Kreiman said.<\/p>\n<p>Areas such as language and common sense are themselves great challenges for the AI community. But it remains to be seen whether they can be solved separately and integrated together along with vision, or integration itself is the key to solving all of them.<\/p>\n<p>\u201cAt some point we need to get into all of these other aspects of cognition, and it is hard to imagine how to integrate cognition without any reference to language and logic,\u201d Kreiman said. \u201cI expect that there will be major exciting efforts in the years to come incorporating more of language and logic in vision models (and conversely incorporating vision into language models as well).\u201d<\/p>\n<div class=\"c-richText c-richText--large\">\n<div class=\"wp-block-image\">\n<p><i><span>This article was originally published by Ben Dickson on\u00a0<\/span><\/i><a rel=\"nofollow noopener\" target=\"_blank\" href=\"https:\/\/bdtechtalks.com\/\"><i><span>TechTalks<\/span><\/i><\/a><i><span>, a publication that examines trends in technology, how they affect the way we live and do business, and the problems they solve. But we also discuss the evil side of technology, the darker implications of new tech, and what we need to look out for. You can read the original article\u00a0<a rel=\"nofollow noopener\" target=\"_blank\" href=\"https:\/\/bdtechtalks.com\/2021\/05\/10\/biological-computer-vision\/\">here<\/a>.<\/span><\/i><\/p>\n<\/div>\n<\/div>\n<\/div>\n<p><script async src=\"\/\/platform.twitter.com\/widgets.js\" charset=\"utf-8\"><\/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\/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\/whats-the-difference-between-human-eyes-and-computer-vision\" target=\"_blank\" rel=\"noopener\">Source<\/a><\/span><\/p>\n","protected":false},"excerpt":{"rendered":"<p>&#8220;#What\u2019s the difference between human eyes and computer vision?&#8221; Since the early years of artificial intelligence, scientists have dreamed of creating computers that can \u201csee\u201d the world. As vision plays a key role in many things we do every day, cracking the code of\u00a0computer vision\u00a0seemed to be one of the major steps toward developing artificial&#8230;<\/p>\n","protected":false},"author":1,"featured_media":256797,"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\/2021\/05\/eye-balls.jpg&signature=9ce4c169ea5b7d0c43fdc3ee07f0db4b","fifu_image_alt":"","footnotes":""},"categories":[18],"tags":[],"class_list":["post-256796","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\/256796","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=256796"}],"version-history":[{"count":0,"href":"https:\/\/buradabiliyorum.com\/en\/wp-json\/wp\/v2\/posts\/256796\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/buradabiliyorum.com\/en\/wp-json\/wp\/v2\/media\/256797"}],"wp:attachment":[{"href":"https:\/\/buradabiliyorum.com\/en\/wp-json\/wp\/v2\/media?parent=256796"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/buradabiliyorum.com\/en\/wp-json\/wp\/v2\/categories?post=256796"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/buradabiliyorum.com\/en\/wp-json\/wp\/v2\/tags?post=256796"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}