{"id":5327,"date":"2024-03-20T17:47:18","date_gmt":"2024-03-20T16:47:18","guid":{"rendered":"https:\/\/pmf-research.eu\/?p=5327"},"modified":"2024-03-21T09:34:19","modified_gmt":"2024-03-21T08:34:19","slug":"deep-neural-network-artificial-intelligence-ai","status":"publish","type":"post","link":"https:\/\/pmf-research.eu\/en\/deep-neural-network-artificial-intelligence-ai\/","title":{"rendered":"Deep neural networks: what they are and why they are revolutionising AI"},"content":{"rendered":"\t\t<div data-elementor-type=\"wp-post\" data-elementor-id=\"5327\" class=\"elementor elementor-5327 elementor-5312\" data-elementor-post-type=\"post\">\n\t\t\t\t\t\t<section class=\"elementor-section elementor-top-section elementor-element elementor-element-ffa881e elementor-section-boxed elementor-section-height-default elementor-section-height-default\" data-id=\"ffa881e\" data-element_type=\"section\" data-e-type=\"section\">\n\t\t\t\t\t\t<div class=\"elementor-container elementor-column-gap-no\">\n\t\t\t\t\t<div class=\"elementor-column elementor-col-100 elementor-top-column elementor-element elementor-element-9ee7371\" data-id=\"9ee7371\" data-element_type=\"column\" data-e-type=\"column\">\n\t\t\t<div class=\"elementor-widget-wrap elementor-element-populated\">\n\t\t\t\t\t\t<div class=\"elementor-element elementor-element-ec88e07 elementor-widget elementor-widget-text-editor\" data-id=\"ec88e07\" data-element_type=\"widget\" data-e-type=\"widget\" data-widget_type=\"text-editor.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t\t\t\t\t\t\t<p><strong>Deep neural networks<\/strong> are at the heart of today\u2019s <strong>artificial intelligence<\/strong> (<strong>AI<\/strong>). Inspired by the structure of the <strong>human brain<\/strong>, they have become synonymous with technological progress and innovation.<\/p><p>Read on to find out more.<\/p>\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-b7be342 elementor-toc--minimized-on-tablet elementor-widget elementor-widget-table-of-contents\" data-id=\"b7be342\" data-element_type=\"widget\" data-e-type=\"widget\" data-settings=\"{&quot;headings_by_tags&quot;:[&quot;h2&quot;,&quot;h3&quot;,&quot;h4&quot;],&quot;exclude_headings_by_selector&quot;:[],&quot;marker_view&quot;:&quot;numbers&quot;,&quot;no_headings_message&quot;:&quot;No headings were found on this page.&quot;,&quot;minimize_box&quot;:&quot;yes&quot;,&quot;minimized_on&quot;:&quot;tablet&quot;,&quot;hierarchical_view&quot;:&quot;yes&quot;,&quot;min_height&quot;:{&quot;unit&quot;:&quot;px&quot;,&quot;size&quot;:&quot;&quot;,&quot;sizes&quot;:[]},&quot;min_height_tablet&quot;:{&quot;unit&quot;:&quot;px&quot;,&quot;size&quot;:&quot;&quot;,&quot;sizes&quot;:[]},&quot;min_height_mobile&quot;:{&quot;unit&quot;:&quot;px&quot;,&quot;size&quot;:&quot;&quot;,&quot;sizes&quot;:[]}}\" data-widget_type=\"table-of-contents.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t\t\t\t\t\t\t<div class=\"elementor-toc__header\">\n\t\t\t\t\t\t<h4 class=\"elementor-toc__header-title\">\n\t\t\t\tTable of contents\t\t\t<\/h4>\n\t\t\t\t\t\t\t\t\t\t<div class=\"elementor-toc__toggle-button elementor-toc__toggle-button--expand\" role=\"button\" tabindex=\"0\" aria-controls=\"elementor-toc__b7be342\" aria-expanded=\"true\" aria-label=\"Open table of contents\"><svg aria-hidden=\"true\" class=\"e-font-icon-svg e-fas-chevron-down\" viewBox=\"0 0 448 512\" xmlns=\"http:\/\/www.w3.org\/2000\/svg\"><path d=\"M207.029 381.476L12.686 187.132c-9.373-9.373-9.373-24.569 0-33.941l22.667-22.667c9.357-9.357 24.522-9.375 33.901-.04L224 284.505l154.745-154.021c9.379-9.335 24.544-9.317 33.901.04l22.667 22.667c9.373 9.373 9.373 24.569 0 33.941L240.971 381.476c-9.373 9.372-24.569 9.372-33.942 0z\"><\/path><\/svg><\/div>\n\t\t\t\t<div class=\"elementor-toc__toggle-button elementor-toc__toggle-button--collapse\" role=\"button\" tabindex=\"0\" aria-controls=\"elementor-toc__b7be342\" aria-expanded=\"true\" aria-label=\"Close table of contents\"><svg aria-hidden=\"true\" class=\"e-font-icon-svg e-fas-chevron-up\" viewBox=\"0 0 448 512\" xmlns=\"http:\/\/www.w3.org\/2000\/svg\"><path d=\"M240.971 130.524l194.343 194.343c9.373 9.373 9.373 24.569 0 33.941l-22.667 22.667c-9.357 9.357-24.522 9.375-33.901.04L224 227.495 69.255 381.516c-9.379 9.335-24.544 9.317-33.901-.04l-22.667-22.667c-9.373-9.373-9.373-24.569 0-33.941L207.03 130.525c9.372-9.373 24.568-9.373 33.941-.001z\"><\/path><\/svg><\/div>\n\t\t\t\t\t<\/div>\n\t\t\t\t<div id=\"elementor-toc__b7be342\" class=\"elementor-toc__body\">\n\t\t\t<div class=\"elementor-toc__spinner-container\">\n\t\t\t\t<svg class=\"elementor-toc__spinner eicon-animation-spin e-font-icon-svg e-eicon-loading\" aria-hidden=\"true\" viewBox=\"0 0 1000 1000\" xmlns=\"http:\/\/www.w3.org\/2000\/svg\"><path d=\"M500 975V858C696 858 858 696 858 500S696 142 500 142 142 304 142 500H25C25 237 238 25 500 25S975 237 975 500 763 975 500 975Z\"><\/path><\/svg>\t\t\t<\/div>\n\t\t<\/div>\n\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-bed69b5 elementor-widget elementor-widget-heading\" data-id=\"bed69b5\" data-element_type=\"widget\" data-e-type=\"widget\" data-widget_type=\"heading.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t\t\t<h2 class=\"elementor-heading-title elementor-size-default\">What are deep neural networks?<\/h2>\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-1311aed elementor-widget elementor-widget-text-editor\" data-id=\"1311aed\" data-element_type=\"widget\" data-e-type=\"widget\" data-widget_type=\"text-editor.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t\t\t\t\t\t\t<p>Deep neural networks are <strong>advanced computational architectures <\/strong>that mimic the functioning of the human brain. A deep neural network uses a large number of processing layers, called &#8216;hidden layers&#8217;, to automatically learn patterns and abstract representations from the raw data, without the need to manually design features.<\/p><p>Each layer is &#8216;<strong>deep<\/strong>&#8216; precisely because it works in synergy with the others to identify and interpret complex data patterns. The more layers the network has, the more intelligent it is. Between each layer, numerous interconnected <strong>artificial neurons<\/strong>, thanks to <a href=\"https:\/\/pmf-research.eu\/en\/deep-learning-machine-learning-traditional-ai\/\"><strong>deep learning<\/strong><\/a> algorithms (such as <strong>backpropagation<\/strong>), process the data and progressively adjust the weight of each connection to minimise errors.<\/p>\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-07fedb8 elementor-widget elementor-widget-heading\" data-id=\"07fedb8\" data-element_type=\"widget\" data-e-type=\"widget\" data-widget_type=\"heading.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t\t\t<h2 class=\"elementor-heading-title elementor-size-default\">Deep neural network types<\/h2>\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-97d5baf elementor-widget elementor-widget-text-editor\" data-id=\"97d5baf\" data-element_type=\"widget\" data-e-type=\"widget\" data-widget_type=\"text-editor.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t\t\t\t\t\t\t<p>There are different <strong>architectures<\/strong> of deep neural networks:<\/p>\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-6d7e13a elementor-widget elementor-widget-heading\" data-id=\"6d7e13a\" data-element_type=\"widget\" data-e-type=\"widget\" data-widget_type=\"heading.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t\t\t<h3 class=\"elementor-heading-title elementor-size-default\">1. Convolutional neural networks<\/h3>\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-457f04d elementor-widget elementor-widget-text-editor\" data-id=\"457f04d\" data-element_type=\"widget\" data-e-type=\"widget\" data-widget_type=\"text-editor.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t\t\t\t\t\t\t<p><strong>Convolutional neural networks<\/strong> excel in <strong>images and videos<\/strong> processing and are so called because they use convolutional layers to extract local features.<\/p><p>Specifically, they are designed to process data with a <strong>grid structure<\/strong>, such as images. They take their name from the <strong>mathematical operation of convolution<\/strong>, which is used to filter and transform input data.<\/p><p>They use convolutional layers to automatically extract features and hierarchies from images, which makes them particularly effective for <a href=\"https:\/\/pmf-research.eu\/en\/computer-vision-what-it-is-areas-of-application\/\"><strong>computer vision<\/strong><\/a> tasks such as <strong>classification<\/strong>, <strong>object detection<\/strong> and <strong>segmentation<\/strong>.<\/p>\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-2acbf4b elementor-widget elementor-widget-heading\" data-id=\"2acbf4b\" data-element_type=\"widget\" data-e-type=\"widget\" data-widget_type=\"heading.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t\t\t<h3 class=\"elementor-heading-title elementor-size-default\">2. Recurrent neural networks<\/h3>\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-6f569b8 elementor-widget elementor-widget-text-editor\" data-id=\"6f569b8\" data-element_type=\"widget\" data-e-type=\"widget\" data-widget_type=\"text-editor.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t\t\t\t\t\t\t<p><strong>Recurrent neural networks <\/strong>are ideal for processing sequential data such as <strong>text and audio<\/strong> due to their ability to store information over time.<\/p><p>Recurrent neural networks have &#8216;feedback connections&#8217; that allow them to maintain an internal memory of past inputs and thus capture long-term contextual data, making them suitable for tasks such as <strong>machine translation<\/strong>, <strong>speech recognition<\/strong> and <strong>text generation<\/strong>.<\/p>\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-b3bb325 elementor-widget elementor-widget-heading\" data-id=\"b3bb325\" data-element_type=\"widget\" data-e-type=\"widget\" data-widget_type=\"heading.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t\t\t<h3 class=\"elementor-heading-title elementor-size-default\">3. Graph neural networks<\/h3>\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-347a99e elementor-widget elementor-widget-text-editor\" data-id=\"347a99e\" data-element_type=\"widget\" data-e-type=\"widget\" data-widget_type=\"text-editor.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t\t\t\t\t\t\t<p><strong>Graph neural networks<\/strong> learn <strong>vector representations of nodes<\/strong> (the entities or objects in the context of the query), incorporating information about the structure of the graph and the attributes of the nodes themselves; this makes them applicable to a wide range of domains, such as <strong>social network analysis<\/strong>, <strong>computational chemistry<\/strong>, <strong>bioinformatics<\/strong> and <strong>recommendation systems<\/strong>.<\/p>\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-bbe8e97 elementor-widget elementor-widget-heading\" data-id=\"bbe8e97\" data-element_type=\"widget\" data-e-type=\"widget\" data-widget_type=\"heading.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t\t\t<h3 class=\"elementor-heading-title elementor-size-default\">4. Autoencoder neural networks<\/h3>\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-50fa7af elementor-widget elementor-widget-text-editor\" data-id=\"50fa7af\" data-element_type=\"widget\" data-e-type=\"widget\" data-widget_type=\"text-editor.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t\t\t\t\t\t\t<p><strong>Autoencoders<\/strong> are a type of <strong>unsupervised neural network<\/strong> used for learning <strong>compressed representations<\/strong> of input data. They consist of an encoding, which maps the input data into a smaller latent representation, and a decoding, which reconstructs the original data from the latent representation.<\/p><p>By training the autoencoder to minimise the reconstruction error, they will be able to learn to capture the salient features and underlying structures of the data. Autoencoders find application in <strong>dimensionality reduction<\/strong>, <strong>denoising<\/strong>, <strong>feature learning<\/strong> and <strong>new data generation<\/strong>.<\/p><p>Each of the architectures described here can be combined with the others in various ways to create specialised neural networks.<\/p>\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-55547d2 elementor-widget elementor-widget-image\" data-id=\"55547d2\" data-element_type=\"widget\" data-e-type=\"widget\" data-widget_type=\"image.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t<img fetchpriority=\"high\" decoding=\"async\" width=\"1400\" height=\"760\" src=\"https:\/\/media.pmf-research.eu\/pmf-research.eu\/wp-content\/uploads\/2024\/03\/Deep-neural-network-2-EN.jpg\" class=\"attachment-full size-full wp-image-5333\" alt=\"deep neural network\" srcset=\"https:\/\/media.pmf-research.eu\/pmf-research.eu\/wp-content\/uploads\/2024\/03\/Deep-neural-network-2-EN.jpg 1400w, https:\/\/media.pmf-research.eu\/pmf-research.eu\/wp-content\/uploads\/2024\/03\/Deep-neural-network-2-EN-300x163.jpg 300w, https:\/\/media.pmf-research.eu\/pmf-research.eu\/wp-content\/uploads\/2024\/03\/Deep-neural-network-2-EN-1024x556.jpg 1024w, https:\/\/media.pmf-research.eu\/pmf-research.eu\/wp-content\/uploads\/2024\/03\/Deep-neural-network-2-EN-768x417.jpg 768w\" sizes=\"(max-width: 1400px) 100vw, 1400px\" \/>\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-cdf6de2 elementor-widget elementor-widget-heading\" data-id=\"cdf6de2\" data-element_type=\"widget\" data-e-type=\"widget\" data-widget_type=\"heading.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t\t\t<h2 class=\"elementor-heading-title elementor-size-default\">Deep neural network applications<\/h2>\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-054c69f elementor-widget elementor-widget-text-editor\" data-id=\"054c69f\" data-element_type=\"widget\" data-e-type=\"widget\" data-widget_type=\"text-editor.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t\t\t\t\t\t\t<p>Deep neural networks, as is evident, are used in a wide range of <a href=\"https:\/\/pmf-research.eu\/en\/ai-applications-artificial-intelligence\/\"><strong>AI applications<\/strong><\/a>, including:<\/p>\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-040c666 elementor-icon-list--layout-traditional elementor-list-item-link-full_width elementor-widget elementor-widget-icon-list\" data-id=\"040c666\" data-element_type=\"widget\" data-e-type=\"widget\" data-widget_type=\"icon-list.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t\t\t\t\t<ul class=\"elementor-icon-list-items\">\n\t\t\t\t\t\t\t<li class=\"elementor-icon-list-item\">\n\t\t\t\t\t\t\t\t\t\t\t<span class=\"elementor-icon-list-icon\">\n\t\t\t\t\t\t\t<svg aria-hidden=\"true\" class=\"e-font-icon-svg e-fas-check\" viewBox=\"0 0 512 512\" xmlns=\"http:\/\/www.w3.org\/2000\/svg\"><path d=\"M173.898 439.404l-166.4-166.4c-9.997-9.997-9.997-26.206 0-36.204l36.203-36.204c9.997-9.998 26.207-9.998 36.204 0L192 312.69 432.095 72.596c9.997-9.997 26.207-9.997 36.204 0l36.203 36.204c9.997 9.997 9.997 26.206 0 36.204l-294.4 294.401c-9.998 9.997-26.207 9.997-36.204-.001z\"><\/path><\/svg>\t\t\t\t\t\t<\/span>\n\t\t\t\t\t\t\t\t\t\t<span class=\"elementor-icon-list-text\">image and video recognition<\/span>\n\t\t\t\t\t\t\t\t\t<\/li>\n\t\t\t\t\t\t\t\t<li class=\"elementor-icon-list-item\">\n\t\t\t\t\t\t\t\t\t\t\t<span class=\"elementor-icon-list-icon\">\n\t\t\t\t\t\t\t<svg aria-hidden=\"true\" class=\"e-font-icon-svg e-fas-check\" viewBox=\"0 0 512 512\" xmlns=\"http:\/\/www.w3.org\/2000\/svg\"><path d=\"M173.898 439.404l-166.4-166.4c-9.997-9.997-9.997-26.206 0-36.204l36.203-36.204c9.997-9.998 26.207-9.998 36.204 0L192 312.69 432.095 72.596c9.997-9.997 26.207-9.997 36.204 0l36.203 36.204c9.997 9.997 9.997 26.206 0 36.204l-294.4 294.401c-9.998 9.997-26.207 9.997-36.204-.001z\"><\/path><\/svg>\t\t\t\t\t\t<\/span>\n\t\t\t\t\t\t\t\t\t\t<span class=\"elementor-icon-list-text\">natural language processing;<\/span>\n\t\t\t\t\t\t\t\t\t<\/li>\n\t\t\t\t\t\t\t\t<li class=\"elementor-icon-list-item\">\n\t\t\t\t\t\t\t\t\t\t\t<span class=\"elementor-icon-list-icon\">\n\t\t\t\t\t\t\t<svg aria-hidden=\"true\" class=\"e-font-icon-svg e-fas-check\" viewBox=\"0 0 512 512\" xmlns=\"http:\/\/www.w3.org\/2000\/svg\"><path d=\"M173.898 439.404l-166.4-166.4c-9.997-9.997-9.997-26.206 0-36.204l36.203-36.204c9.997-9.998 26.207-9.998 36.204 0L192 312.69 432.095 72.596c9.997-9.997 26.207-9.997 36.204 0l36.203 36.204c9.997 9.997 9.997 26.206 0 36.204l-294.4 294.401c-9.998 9.997-26.207 9.997-36.204-.001z\"><\/path><\/svg>\t\t\t\t\t\t<\/span>\n\t\t\t\t\t\t\t\t\t\t<span class=\"elementor-icon-list-text\">speech synthesis and recognition;<\/span>\n\t\t\t\t\t\t\t\t\t<\/li>\n\t\t\t\t\t\t\t\t<li class=\"elementor-icon-list-item\">\n\t\t\t\t\t\t\t\t\t\t\t<span class=\"elementor-icon-list-icon\">\n\t\t\t\t\t\t\t<svg aria-hidden=\"true\" class=\"e-font-icon-svg e-fas-check\" viewBox=\"0 0 512 512\" xmlns=\"http:\/\/www.w3.org\/2000\/svg\"><path d=\"M173.898 439.404l-166.4-166.4c-9.997-9.997-9.997-26.206 0-36.204l36.203-36.204c9.997-9.998 26.207-9.998 36.204 0L192 312.69 432.095 72.596c9.997-9.997 26.207-9.997 36.204 0l36.203 36.204c9.997 9.997 9.997 26.206 0 36.204l-294.4 294.401c-9.998 9.997-26.207 9.997-36.204-.001z\"><\/path><\/svg>\t\t\t\t\t\t<\/span>\n\t\t\t\t\t\t\t\t\t\t<span class=\"elementor-icon-list-text\">autonomous driving;<\/span>\n\t\t\t\t\t\t\t\t\t<\/li>\n\t\t\t\t\t\t\t\t<li class=\"elementor-icon-list-item\">\n\t\t\t\t\t\t\t\t\t\t\t<span class=\"elementor-icon-list-icon\">\n\t\t\t\t\t\t\t<svg aria-hidden=\"true\" class=\"e-font-icon-svg e-fas-check\" viewBox=\"0 0 512 512\" xmlns=\"http:\/\/www.w3.org\/2000\/svg\"><path d=\"M173.898 439.404l-166.4-166.4c-9.997-9.997-9.997-26.206 0-36.204l36.203-36.204c9.997-9.998 26.207-9.998 36.204 0L192 312.69 432.095 72.596c9.997-9.997 26.207-9.997 36.204 0l36.203 36.204c9.997 9.997 9.997 26.206 0 36.204l-294.4 294.401c-9.998 9.997-26.207 9.997-36.204-.001z\"><\/path><\/svg>\t\t\t\t\t\t<\/span>\n\t\t\t\t\t\t\t\t\t\t<span class=\"elementor-icon-list-text\">medical diagnosis;<\/span>\n\t\t\t\t\t\t\t\t\t<\/li>\n\t\t\t\t\t\t\t\t<li class=\"elementor-icon-list-item\">\n\t\t\t\t\t\t\t\t\t\t\t<span class=\"elementor-icon-list-icon\">\n\t\t\t\t\t\t\t<svg aria-hidden=\"true\" class=\"e-font-icon-svg e-fas-check\" viewBox=\"0 0 512 512\" xmlns=\"http:\/\/www.w3.org\/2000\/svg\"><path d=\"M173.898 439.404l-166.4-166.4c-9.997-9.997-9.997-26.206 0-36.204l36.203-36.204c9.997-9.998 26.207-9.998 36.204 0L192 312.69 432.095 72.596c9.997-9.997 26.207-9.997 36.204 0l36.203 36.204c9.997 9.997 9.997 26.206 0 36.204l-294.4 294.401c-9.998 9.997-26.207 9.997-36.204-.001z\"><\/path><\/svg>\t\t\t\t\t\t<\/span>\n\t\t\t\t\t\t\t\t\t\t<span class=\"elementor-icon-list-text\">drug discovery;<\/span>\n\t\t\t\t\t\t\t\t\t<\/li>\n\t\t\t\t\t\t\t\t<li class=\"elementor-icon-list-item\">\n\t\t\t\t\t\t\t\t\t\t\t<span class=\"elementor-icon-list-icon\">\n\t\t\t\t\t\t\t<svg aria-hidden=\"true\" class=\"e-font-icon-svg e-fas-check\" viewBox=\"0 0 512 512\" xmlns=\"http:\/\/www.w3.org\/2000\/svg\"><path d=\"M173.898 439.404l-166.4-166.4c-9.997-9.997-9.997-26.206 0-36.204l36.203-36.204c9.997-9.998 26.207-9.998 36.204 0L192 312.69 432.095 72.596c9.997-9.997 26.207-9.997 36.204 0l36.203 36.204c9.997 9.997 9.997 26.206 0 36.204l-294.4 294.401c-9.998 9.997-26.207 9.997-36.204-.001z\"><\/path><\/svg>\t\t\t\t\t\t<\/span>\n\t\t\t\t\t\t\t\t\t\t<span class=\"elementor-icon-list-text\">machine translation;<\/span>\n\t\t\t\t\t\t\t\t\t<\/li>\n\t\t\t\t\t\t\t\t<li class=\"elementor-icon-list-item\">\n\t\t\t\t\t\t\t\t\t\t\t<span class=\"elementor-icon-list-icon\">\n\t\t\t\t\t\t\t<svg aria-hidden=\"true\" class=\"e-font-icon-svg e-fas-check\" viewBox=\"0 0 512 512\" xmlns=\"http:\/\/www.w3.org\/2000\/svg\"><path d=\"M173.898 439.404l-166.4-166.4c-9.997-9.997-9.997-26.206 0-36.204l36.203-36.204c9.997-9.998 26.207-9.998 36.204 0L192 312.69 432.095 72.596c9.997-9.997 26.207-9.997 36.204 0l36.203 36.204c9.997 9.997 9.997 26.206 0 36.204l-294.4 294.401c-9.998 9.997-26.207 9.997-36.204-.001z\"><\/path><\/svg>\t\t\t\t\t\t<\/span>\n\t\t\t\t\t\t\t\t\t\t<span class=\"elementor-icon-list-text\">complex games.<\/span>\n\t\t\t\t\t\t\t\t\t<\/li>\n\t\t\t\t\t\t<\/ul>\n\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-0113383 elementor-widget elementor-widget-text-editor\" data-id=\"0113383\" data-element_type=\"widget\" data-e-type=\"widget\" data-widget_type=\"text-editor.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t\t\t\t\t\t\t<p>In each of the above fields, deep neural networks have reached and surpassed human performance, opening the way to new possibilities.<\/p>\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-01237da elementor-widget elementor-widget-heading\" data-id=\"01237da\" data-element_type=\"widget\" data-e-type=\"widget\" data-widget_type=\"heading.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t\t\t<h2 class=\"elementor-heading-title elementor-size-default\">Future challenges and opportunities<\/h2>\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-b4711e9 elementor-widget elementor-widget-text-editor\" data-id=\"b4711e9\" data-element_type=\"widget\" data-e-type=\"widget\" data-widget_type=\"text-editor.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t\t\t\t\t\t\t<p>In spite of the invention of <strong>neuromorphic CPUs and GPUs<\/strong>, which accelerate machine learning, effectively decreeing an epochal turning point in the evolution of artificial intelligence, the greatest difficulty lies in fully interpreting their <strong>decision-making process<\/strong>.<\/p><p>Researchers around the world are working side by side, every day, to solve the puzzle and develop <strong>networks that are safer<\/strong>, before being more powerful. Any drift and <strong>loss of control of AI<\/strong> could have catastrophic consequences.<\/p><p>The most significant challenges undoubtedly concern:<\/p>\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-11c6478 elementor-widget elementor-widget-heading\" data-id=\"11c6478\" data-element_type=\"widget\" data-e-type=\"widget\" data-widget_type=\"heading.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t\t\t<h3 class=\"elementor-heading-title elementor-size-default\">Impenetrability<\/h3>\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-7a95ac3 elementor-widget elementor-widget-text-editor\" data-id=\"7a95ac3\" data-element_type=\"widget\" data-e-type=\"widget\" data-widget_type=\"text-editor.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t\t\t\t\t\t\t<p>As mentioned above, deep neural networks are often referred to as &#8216;<strong>black boxes<\/strong>&#8216; because they are &#8216;<strong>impenetrable<\/strong>&#8216; in the sense that it is not clear how they make decisions.<\/p>\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-b674170 elementor-widget elementor-widget-heading\" data-id=\"b674170\" data-element_type=\"widget\" data-e-type=\"widget\" data-widget_type=\"heading.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t\t\t<h3 class=\"elementor-heading-title elementor-size-default\"> Robustness<\/h3>\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-0decae0 elementor-widget elementor-widget-text-editor\" data-id=\"0decae0\" data-element_type=\"widget\" data-e-type=\"widget\" data-widget_type=\"text-editor.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t\t\t\t\t\t\t<p>Thousands of examples can be found on the net, specifically designed to deceive networks; some of which raise serious concerns about their &#8216;<strong>robustness<\/strong>&#8216;.<\/p>\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-8bdbd14 elementor-widget elementor-widget-heading\" data-id=\"8bdbd14\" data-element_type=\"widget\" data-e-type=\"widget\" data-widget_type=\"heading.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t\t\t<h3 class=\"elementor-heading-title elementor-size-default\">Hardware<\/h3>\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-7feabc3 elementor-widget elementor-widget-text-editor\" data-id=\"7feabc3\" data-element_type=\"widget\" data-e-type=\"widget\" data-widget_type=\"text-editor.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t\t\t\t\t\t\t<p>Training large amounts of data requires <strong>powerful hardware<\/strong> that is often not easy to find.<\/p>\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-6d42c31 elementor-widget elementor-widget-image\" data-id=\"6d42c31\" data-element_type=\"widget\" data-e-type=\"widget\" data-widget_type=\"image.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t<a href=\"https:\/\/pmf-research.eu\/en\/#contact-us\" target=\"_blank\">\n\t\t\t\t\t\t\t<img decoding=\"async\" width=\"1400\" height=\"760\" src=\"https:\/\/media.pmf-research.eu\/pmf-research.eu\/wp-content\/uploads\/2024\/03\/Deep-neural-network-3-EN.jpg\" class=\"attachment-full size-full wp-image-5335\" alt=\"deep neural network\" srcset=\"https:\/\/media.pmf-research.eu\/pmf-research.eu\/wp-content\/uploads\/2024\/03\/Deep-neural-network-3-EN.jpg 1400w, https:\/\/media.pmf-research.eu\/pmf-research.eu\/wp-content\/uploads\/2024\/03\/Deep-neural-network-3-EN-300x163.jpg 300w, https:\/\/media.pmf-research.eu\/pmf-research.eu\/wp-content\/uploads\/2024\/03\/Deep-neural-network-3-EN-1024x556.jpg 1024w, https:\/\/media.pmf-research.eu\/pmf-research.eu\/wp-content\/uploads\/2024\/03\/Deep-neural-network-3-EN-768x417.jpg 768w\" sizes=\"(max-width: 1400px) 100vw, 1400px\" \/>\t\t\t\t\t\t\t\t<\/a>\n\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-3f39aa0 elementor-widget elementor-widget-heading\" data-id=\"3f39aa0\" data-element_type=\"widget\" data-e-type=\"widget\" data-widget_type=\"heading.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t\t\t<h2 class=\"elementor-heading-title elementor-size-default\">Contact us for deep neural network projects<\/h2>\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-ada179e elementor-widget elementor-widget-text-editor\" data-id=\"ada179e\" data-element_type=\"widget\" data-e-type=\"widget\" data-widget_type=\"text-editor.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t\t\t\t\t\t\t<p><strong>PMF Research<\/strong> is a <strong>research and development<\/strong> (<strong>R&amp;D<\/strong>) centre established in 2003 and part of the <a href=\"https:\/\/www.jogroup.eu\/en\/\" target=\"_blank\" rel=\"noopener\"><strong>JO Group<\/strong><\/a> cluster of companies; it focuses on ICT, virtual reality, artificial intelligence and big data.<\/p><p>If you are looking for a reliable partner in the field of artificial intelligence, contact us. You can fill in the <strong>contact form<\/strong> or call <strong>+390957225331<\/strong>.<\/p>\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/section>\n\t\t\t\t<\/div>\n\t\t","protected":false},"excerpt":{"rendered":"<p>Deep neural networks are at the heart of today\u2019s artificial intelligence (AI). Inspired by the structure of the human brain, they have become synonymous with technological progress and innovation. Read on to find out more. Table of contents &nbsp; What are deep neural networks? Deep neural networks are advanced computational architectures that mimic the functioning [&hellip;]<\/p>\n","protected":false},"author":8,"featured_media":5330,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"site-sidebar-layout":"default","site-content-layout":"","ast-site-content-layout":"default","site-content-style":"default","site-sidebar-style":"default","ast-global-header-display":"","ast-banner-title-visibility":"","ast-main-header-display":"","ast-hfb-above-header-display":"","ast-hfb-below-header-display":"","ast-hfb-mobile-header-display":"","site-post-title":"","ast-breadcrumbs-content":"","ast-featured-img":"","footer-sml-layout":"","ast-disable-related-posts":"","theme-transparent-header-meta":"default","adv-header-id-meta":"","stick-header-meta":"","header-above-stick-meta":"","header-main-stick-meta":"","header-below-stick-meta":"","astra-migrate-meta-layouts":"set","ast-page-background-enabled":"default","ast-page-background-meta":{"desktop":{"background-color":"","background-image":"","background-repeat":"repeat","background-position":"center center","background-size":"auto","background-attachment":"scroll","background-type":"","background-media":"","overlay-type":"","overlay-color":"","overlay-opacity":"","overlay-gradient":""},"tablet":{"background-color":"","background-image":"","background-repeat":"repeat","background-position":"center center","background-size":"auto","background-attachment":"scroll","background-type":"","background-media":"","overlay-type":"","overlay-color":"","overlay-opacity":"","overlay-gradient":""},"mobile":{"background-color":"","background-image":"","background-repeat":"repeat","background-position":"center center","background-size":"auto","background-attachment":"scroll","background-type":"","background-media":"","overlay-type":"","overlay-color":"","overlay-opacity":"","overlay-gradient":""}},"ast-content-background-meta":{"desktop":{"background-color":"var(--ast-global-color-5)","background-image":"","background-repeat":"repeat","background-position":"center center","background-size":"auto","background-attachment":"scroll","background-type":"","background-media":"","overlay-type":"","overlay-color":"","overlay-opacity":"","overlay-gradient":""},"tablet":{"background-color":"var(--ast-global-color-5)","background-image":"","background-repeat":"repeat","background-position":"center center","background-size":"auto","background-attachment":"scroll","background-type":"","background-media":"","overlay-type":"","overlay-color":"","overlay-opacity":"","overlay-gradient":""},"mobile":{"background-color":"var(--ast-global-color-5)","background-image":"","background-repeat":"repeat","background-position":"center center","background-size":"auto","background-attachment":"scroll","background-type":"","background-media":"","overlay-type":"","overlay-color":"","overlay-opacity":"","overlay-gradient":""}},"footnotes":""},"categories":[34],"tags":[],"class_list":["post-5327","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-artificial-intelligence"],"_links":{"self":[{"href":"https:\/\/pmf-research.eu\/en\/wp-json\/wp\/v2\/posts\/5327","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/pmf-research.eu\/en\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/pmf-research.eu\/en\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/pmf-research.eu\/en\/wp-json\/wp\/v2\/users\/8"}],"replies":[{"embeddable":true,"href":"https:\/\/pmf-research.eu\/en\/wp-json\/wp\/v2\/comments?post=5327"}],"version-history":[{"count":5,"href":"https:\/\/pmf-research.eu\/en\/wp-json\/wp\/v2\/posts\/5327\/revisions"}],"predecessor-version":[{"id":5345,"href":"https:\/\/pmf-research.eu\/en\/wp-json\/wp\/v2\/posts\/5327\/revisions\/5345"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/pmf-research.eu\/en\/wp-json\/wp\/v2\/media\/5330"}],"wp:attachment":[{"href":"https:\/\/pmf-research.eu\/en\/wp-json\/wp\/v2\/media?parent=5327"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/pmf-research.eu\/en\/wp-json\/wp\/v2\/categories?post=5327"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/pmf-research.eu\/en\/wp-json\/wp\/v2\/tags?post=5327"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}