{"id":255,"date":"2022-03-24T15:17:11","date_gmt":"2022-03-24T14:17:11","guid":{"rendered":"https:\/\/machinelearning.humanativaspa.it\/en\/?p=255"},"modified":"2023-03-03T14:58:50","modified_gmt":"2023-03-03T13:58:50","slug":"neural-networks-feed-forward-and-recurrent-neural-networks","status":"publish","type":"post","link":"https:\/\/machinelearning.humanativaspa.it\/en\/neural-networks-feed-forward-and-recurrent-neural-networks\/","title":{"rendered":"Neural networks: feed-forward and recurrent neural networks"},"content":{"rendered":"<p><b><span data-contrast=\"auto\">Recurring models (RNNs)<\/span><\/b><span data-ccp-props=\"{&quot;201341983&quot;:0,&quot;335559739&quot;:0,&quot;335559740&quot;:240}\">\u00a0<\/span><span data-ccp-props=\"{&quot;201341983&quot;:0,&quot;335559739&quot;:0,&quot;335559740&quot;:240}\">\u00a0<\/span><\/p>\n<p><span data-contrast=\"auto\">Neural networks can be divided into two main categories: Feed-forward and Recurrent Neural Network (RNN).<\/span><span data-ccp-props=\"{&quot;201341983&quot;:0,&quot;335559739&quot;:0,&quot;335559740&quot;:240}\">\u00a0<\/span><\/p>\n<p><b><span data-contrast=\"auto\">Feed-forwards<\/span><\/b><span data-contrast=\"auto\"> are neural networks, where each input and its output move in only one direction, that means, there are no cycles or backward connections, nor between nodes of the same level. Which in contrast can occur in <\/span><b><span data-contrast=\"auto\">recurrent neural networks (RNNs)<\/span><\/b><span data-contrast=\"auto\">.<\/span><span data-ccp-props=\"{&quot;201341983&quot;:0,&quot;335559739&quot;:0,&quot;335559740&quot;:240}\">\u00a0<\/span><\/p>\n<p><b><span data-contrast=\"auto\">RNN<\/span><\/b><span data-contrast=\"auto\"> is a class of artificial neural networks used in prediction tasks, because it is able to analyze Time Series and predict future trends: e.g. the stock price, the trajectory of a vehicle, the next note in a melody and much more.<\/span><span data-ccp-props=\"{&quot;201341983&quot;:0,&quot;335559739&quot;:0,&quot;335559740&quot;:240}\">\u00a0<\/span><\/p>\n<p><span data-contrast=\"auto\">Generalizing, one of the peculiarities of <\/span><b><span data-contrast=\"auto\">Recurrent Neural Networks<\/span><\/b><span data-contrast=\"auto\"> lies in the ability to work on sequences of <\/span><b><span data-contrast=\"auto\">arbitrary length<\/span><\/b><span data-contrast=\"auto\">, overcoming the limitations, in this sense, imposed by other structures such as <\/span><b><span data-contrast=\"auto\">Convolutional Neural Networks (CNNs)<\/span><\/b><span data-contrast=\"auto\"> which, instead, impose fixed-length inputs.<\/span><span data-ccp-props=\"{&quot;201341983&quot;:0,&quot;335559739&quot;:330,&quot;335559740&quot;:240}\">\u00a0<\/span><\/p>\n<p><b><span data-contrast=\"auto\">Recurrent Neural Networks<\/span><\/b><span data-contrast=\"auto\"> are able to work on:<\/span><span data-ccp-props=\"{&quot;201341983&quot;:0,&quot;335559739&quot;:330,&quot;335559740&quot;:240}\">\u00a0<\/span><\/p>\n<ul>\n<li><span data-contrast=\"auto\"> Sentences and text fragments<\/span><\/li>\n<li><span data-contrast=\"auto\">Audio<\/span><\/li>\n<li><span data-contrast=\"auto\">Documents<\/span><\/li>\n<\/ul>\n<p><span data-contrast=\"auto\">\u00a0<\/span><span data-ccp-props=\"{&quot;201341983&quot;:0,&quot;335559739&quot;:330,&quot;335559740&quot;:240}\">\u00a0<\/span><\/p>\n<p><span data-contrast=\"auto\">Allowing us to solve problems such as:<\/span><span data-ccp-props=\"{&quot;201341983&quot;:0,&quot;335559739&quot;:330,&quot;335559740&quot;:240}\">\u00a0<\/span><\/p>\n<ul>\n<li><span data-contrast=\"auto\"> speech-to-text<\/span><\/li>\n<li><span data-contrast=\"auto\"> Sentiment Analysis (sentiment extraction from phrases, e.g. reviews and social comments)<\/span><\/li>\n<li><span data-contrast=\"auto\"> Automatic translation<\/span><\/li>\n<\/ul>\n<p><span data-ccp-props=\"{&quot;201341983&quot;:0,&quot;335559739&quot;:330,&quot;335559740&quot;:240}\">\u00a0<\/span><\/p>\n<p><span data-contrast=\"auto\">For example, <\/span><b><span data-contrast=\"auto\">RNN<\/span><\/b><span data-contrast=\"auto\"> is a very valuable asset to be used in <\/span><b><span data-contrast=\"auto\">Natural Language Processing (NLP)<\/span><\/b><span data-contrast=\"auto\"> problems.<\/span><span data-ccp-props=\"{&quot;201341983&quot;:0,&quot;335559739&quot;:0,&quot;335559740&quot;:240}\">\u00a0<\/span><\/p>\n<p><span data-contrast=\"auto\">In addition, <\/span><b><span data-contrast=\"auto\">RNN<\/span><\/b><span data-contrast=\"auto\"> networks are surprisingly <\/span><b><span data-contrast=\"auto\">creative<\/span><\/b><span data-contrast=\"auto\">: they are able to pinpoint the next most likely musical notes in a melodic sequence. This can give life to real musical scores entirely written by Artificial Intelligence; an example is the project from <\/span><b><span data-contrast=\"auto\">Google&#8217;s Magenta Project<\/span><\/b><span data-contrast=\"auto\"> that using <\/span><b><span data-contrast=\"auto\">Tensorflow<\/span><\/b><span data-contrast=\"auto\">, provides an ML framework for musical compositions.<\/span><span data-ccp-props=\"{&quot;201341983&quot;:0,&quot;335559739&quot;:0,&quot;335559740&quot;:240}\">\u00a0<\/span><\/p>\n<p><a href=\"https:\/\/magenta.tensorflow.org\/\"><span data-contrast=\"auto\">https:\/\/magenta.tensorflow.org<\/span><\/a><span data-ccp-props=\"{&quot;201341983&quot;:0,&quot;335559739&quot;:0,&quot;335559740&quot;:240}\">\u00a0<\/span><\/p>\n<p><span data-ccp-props=\"{&quot;201341983&quot;:0,&quot;335559739&quot;:0,&quot;335559740&quot;:240}\">\u00a0<\/span><\/p>\n<p><span data-contrast=\"auto\">A <\/span><b><span data-contrast=\"auto\">recurrent neural network<\/span><\/b><span data-contrast=\"auto\"> is similar to <\/span><b><span data-contrast=\"auto\">feed-forward<\/span><\/b><span data-contrast=\"auto\"> networks, except for the presence of a connection pointing brackward.<\/span><span data-ccp-props=\"{&quot;201341983&quot;:0,&quot;335559739&quot;:0,&quot;335559740&quot;:240}\">\u00a0<\/span><\/p>\n<p><span data-contrast=\"auto\">To better understand this structure, consider the simplest example of <\/span><b><span data-contrast=\"auto\">RNN<\/span><\/b><span data-contrast=\"auto\">: a single neuron that receives an input, produces an output, and sends it back to itself.<\/span><span data-ccp-props=\"{&quot;201341983&quot;:0,&quot;335559739&quot;:0,&quot;335559740&quot;:240}\">\u00a0<\/span><\/p>\n<p><span data-ccp-props=\"{&quot;201341983&quot;:0,&quot;335559739&quot;:0,&quot;335559740&quot;:240}\">\u00a0<\/span><\/p>\n<p><span data-ccp-props=\"{&quot;201341983&quot;:0,&quot;335559739&quot;:330,&quot;335559740&quot;:240}\"> <img loading=\"lazy\" decoding=\"async\" class=\"alignnone wp-image-256 size-full\" src=\"https:\/\/machinelearning.humanativaspa.it\/en\/wp-content\/uploads\/sites\/4\/2023\/03\/1-5.jpg\" alt=\"\" width=\"600\" height=\"402\" srcset=\"https:\/\/machinelearning.humanativaspa.it\/en\/wp-content\/uploads\/sites\/4\/2023\/03\/1-5.jpg 600w, https:\/\/machinelearning.humanativaspa.it\/en\/wp-content\/uploads\/sites\/4\/2023\/03\/1-5-300x201.jpg 300w\" sizes=\"auto, (max-width: 600px) 100vw, 600px\" \/><\/span><\/p>\n<p><span data-contrast=\"auto\">\u202f<\/span><span data-ccp-props=\"{&quot;201341983&quot;:0,&quot;335559739&quot;:330,&quot;335559740&quot;:240}\">\u00a0<\/span><\/p>\n<p><span data-contrast=\"auto\">Among the RNNs that best implement this type of solution are the so-called <\/span><b><span data-contrast=\"auto\">Long Short-Term Memory Network (LSTM).<\/span><\/b><span data-ccp-props=\"{&quot;201341983&quot;:0,&quot;335559739&quot;:330,&quot;335559740&quot;:240}\">\u00a0<\/span><\/p>\n<p><span data-contrast=\"auto\">These are particularly suitable when we need to recognize natural language; It will be useful, in this case, to be able to go back in time, even a lot, for each term that we wish to recognize, in order to contextualize the topic at best.<\/span><span data-ccp-props=\"{&quot;201341983&quot;:0,&quot;335559739&quot;:330,&quot;335559740&quot;:240}\">\u00a0<\/span><\/p>\n<p><b><span data-contrast=\"auto\">LSTMs<\/span><\/b><span data-contrast=\"auto\"> typically form chains of recurrent neural networks, each of which applies specific activation functions to filter out different characteristics of the input data, which can be either related to the current word to be predicted, or to those previously stored. We can also say that <\/span><b><span data-contrast=\"auto\">LSTMs<\/span><\/b><span data-contrast=\"auto\"> &#8220;<\/span><i><span data-contrast=\"auto\">have long memory<\/span><\/i><span data-contrast=\"auto\">!&#8221;.<\/span><span data-ccp-props=\"{&quot;201341983&quot;:0,&quot;335559739&quot;:330,&quot;335559740&quot;:240}\">\u00a0<\/span><\/p>\n<p><span data-contrast=\"auto\">A particular use of RNN networks are <\/span><b><span data-contrast=\"auto\">time series<\/span><\/b><span data-contrast=\"auto\">.<\/span><span data-ccp-props=\"{&quot;201341983&quot;:0,&quot;335559739&quot;:330,&quot;335559740&quot;:240}\">\u00a0<\/span><\/p>\n<p><span data-contrast=\"auto\">A time series can be related to the trend over time: of a stock exchange, the temperature of an environment, the energy consumption of a plant, etc.<\/span><span data-ccp-props=\"{&quot;201341983&quot;:0,&quot;335559739&quot;:330,&quot;335559740&quot;:240}\">\u00a0<\/span><\/p>\n<p><span data-contrast=\"auto\">We can consider a time series as a function sampled in several time instants.<\/span><span data-ccp-props=\"{&quot;201341983&quot;:0,&quot;335559739&quot;:330,&quot;335559740&quot;:240}\">\u00a0<\/span><\/p>\n<p><span data-contrast=\"auto\">An example in Tensorflow-Keras of RNN for the prediction of a mathematical function (combination of sinusoids) can be viewed by clicking on the link below:<\/span><span data-ccp-props=\"{&quot;201341983&quot;:0,&quot;335559739&quot;:330,&quot;335559740&quot;:240}\">\u00a0<\/span><\/p>\n<p><a href=\"https:\/\/github.com\/ageron\/handson-ml2\"><span data-contrast=\"auto\">https:\/\/github.com\/ageron\/handson-ml2<\/span><\/a><span data-ccp-props=\"{&quot;201341983&quot;:0,&quot;335559739&quot;:0,&quot;335559740&quot;:240}\">\u00a0<\/span><\/p>\n<p><img loading=\"lazy\" decoding=\"async\" class=\"alignnone wp-image-257 size-full\" src=\"https:\/\/machinelearning.humanativaspa.it\/en\/wp-content\/uploads\/sites\/4\/2023\/03\/2-4.jpg\" alt=\"\" width=\"600\" height=\"483\" srcset=\"https:\/\/machinelearning.humanativaspa.it\/en\/wp-content\/uploads\/sites\/4\/2023\/03\/2-4.jpg 600w, https:\/\/machinelearning.humanativaspa.it\/en\/wp-content\/uploads\/sites\/4\/2023\/03\/2-4-300x242.jpg 300w\" sizes=\"auto, (max-width: 600px) 100vw, 600px\" \/><\/p>\n<p><span data-contrast=\"auto\"><strong>Humanativa is currently working on two different projects regarding this topic<\/strong>:<\/span><span data-ccp-props=\"{&quot;201341983&quot;:0,&quot;335559739&quot;:160,&quot;335559740&quot;:240}\">\u00a0<\/span><\/p>\n<ul>\n<li><span data-contrast=\"auto\"> the first is developed on an analysis based on time series, to analyze the behavior of passengers in an airport and predict the number of those present in the various points (gates, shops, etc &#8230;) a week in advance, with the aim of improving airport quality and safety;<\/span><\/li>\n<li><span data-contrast=\"auto\"> the other is embodied in an analysis of the Sentiment of film reviews, using a neural network that uses LSTM methodologies.<\/span><\/li>\n<\/ul>\n<p><span data-ccp-props=\"{&quot;201341983&quot;:0,&quot;335559739&quot;:160,&quot;335559740&quot;:259}\">\u00a0<\/span><\/p>\n","protected":false},"excerpt":{"rendered":"<p>Recurring models (RNNs)\u00a0\u00a0 Neural networks can be divided into two main categories: Feed-forward and Recurrent Neural Network (RNN).\u00a0 [&hellip;]<\/p>\n","protected":false},"author":1,"featured_media":258,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[56],"tags":[],"class_list":["post-255","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-articoli"],"yoast_head":"<!-- This site is optimized with the Yoast SEO plugin v27.4 - https:\/\/yoast.com\/product\/yoast-seo-wordpress\/ -->\n<title>Neural networks: feed-forward and recurrent neural networks - HN Machine Learning en<\/title>\n<meta name=\"robots\" content=\"index, follow, max-snippet:-1, max-image-preview:large, max-video-preview:-1\" \/>\n<link rel=\"canonical\" href=\"https:\/\/machinelearning.humanativaspa.it\/en\/neural-networks-feed-forward-and-recurrent-neural-networks\/\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:title\" content=\"Neural networks: feed-forward and recurrent neural networks - HN Machine Learning en\" \/>\n<meta name=\"twitter:description\" content=\"Recurring models (RNNs)\u00a0\u00a0 Neural networks can be divided into two main categories: Feed-forward and Recurrent Neural Network (RNN).\u00a0 [&hellip;]\" \/>\n<meta name=\"twitter:image\" content=\"https:\/\/machinelearning.humanativaspa.it\/en\/wp-content\/uploads\/sites\/4\/2023\/03\/reti_neurali_24_03_22_ist.jpg\" \/>\n<meta name=\"twitter:label1\" content=\"Written by\" \/>\n\t<meta name=\"twitter:data1\" content=\"Andream\" \/>\n\t<meta name=\"twitter:label2\" content=\"Estimated reading time\" \/>\n\t<meta name=\"twitter:data2\" content=\"3 minutes\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\\\/\\\/schema.org\",\"@graph\":[{\"@type\":\"Article\",\"@id\":\"https:\\\/\\\/machinelearning.humanativaspa.it\\\/en\\\/neural-networks-feed-forward-and-recurrent-neural-networks\\\/#article\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/machinelearning.humanativaspa.it\\\/en\\\/neural-networks-feed-forward-and-recurrent-neural-networks\\\/\"},\"author\":{\"name\":\"Andream\",\"@id\":\"https:\\\/\\\/machinelearning.humanativaspa.it\\\/en\\\/#\\\/schema\\\/person\\\/a6de167b6fe30bf1d2edfcbfd3417de8\"},\"headline\":\"Neural networks: feed-forward and recurrent neural networks\",\"datePublished\":\"2022-03-24T14:17:11+00:00\",\"dateModified\":\"2023-03-03T13:58:50+00:00\",\"mainEntityOfPage\":{\"@id\":\"https:\\\/\\\/machinelearning.humanativaspa.it\\\/en\\\/neural-networks-feed-forward-and-recurrent-neural-networks\\\/\"},\"wordCount\":579,\"publisher\":{\"@id\":\"https:\\\/\\\/machinelearning.humanativaspa.it\\\/en\\\/#organization\"},\"image\":{\"@id\":\"https:\\\/\\\/machinelearning.humanativaspa.it\\\/en\\\/neural-networks-feed-forward-and-recurrent-neural-networks\\\/#primaryimage\"},\"thumbnailUrl\":\"https:\\\/\\\/machinelearning.humanativaspa.it\\\/en\\\/wp-content\\\/uploads\\\/sites\\\/4\\\/2023\\\/03\\\/reti_neurali_24_03_22_ist.jpg\",\"articleSection\":[\"Articles\"],\"inLanguage\":\"en-GB\"},{\"@type\":\"WebPage\",\"@id\":\"https:\\\/\\\/machinelearning.humanativaspa.it\\\/en\\\/neural-networks-feed-forward-and-recurrent-neural-networks\\\/\",\"url\":\"https:\\\/\\\/machinelearning.humanativaspa.it\\\/en\\\/neural-networks-feed-forward-and-recurrent-neural-networks\\\/\",\"name\":\"Neural networks: feed-forward and recurrent neural networks - HN Machine Learning en\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/machinelearning.humanativaspa.it\\\/en\\\/#website\"},\"primaryImageOfPage\":{\"@id\":\"https:\\\/\\\/machinelearning.humanativaspa.it\\\/en\\\/neural-networks-feed-forward-and-recurrent-neural-networks\\\/#primaryimage\"},\"image\":{\"@id\":\"https:\\\/\\\/machinelearning.humanativaspa.it\\\/en\\\/neural-networks-feed-forward-and-recurrent-neural-networks\\\/#primaryimage\"},\"thumbnailUrl\":\"https:\\\/\\\/machinelearning.humanativaspa.it\\\/en\\\/wp-content\\\/uploads\\\/sites\\\/4\\\/2023\\\/03\\\/reti_neurali_24_03_22_ist.jpg\",\"datePublished\":\"2022-03-24T14:17:11+00:00\",\"dateModified\":\"2023-03-03T13:58:50+00:00\",\"breadcrumb\":{\"@id\":\"https:\\\/\\\/machinelearning.humanativaspa.it\\\/en\\\/neural-networks-feed-forward-and-recurrent-neural-networks\\\/#breadcrumb\"},\"inLanguage\":\"en-GB\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\\\/\\\/machinelearning.humanativaspa.it\\\/en\\\/neural-networks-feed-forward-and-recurrent-neural-networks\\\/\"]}]},{\"@type\":\"ImageObject\",\"inLanguage\":\"en-GB\",\"@id\":\"https:\\\/\\\/machinelearning.humanativaspa.it\\\/en\\\/neural-networks-feed-forward-and-recurrent-neural-networks\\\/#primaryimage\",\"url\":\"https:\\\/\\\/machinelearning.humanativaspa.it\\\/en\\\/wp-content\\\/uploads\\\/sites\\\/4\\\/2023\\\/03\\\/reti_neurali_24_03_22_ist.jpg\",\"contentUrl\":\"https:\\\/\\\/machinelearning.humanativaspa.it\\\/en\\\/wp-content\\\/uploads\\\/sites\\\/4\\\/2023\\\/03\\\/reti_neurali_24_03_22_ist.jpg\",\"width\":1200,\"height\":600},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\\\/\\\/machinelearning.humanativaspa.it\\\/en\\\/neural-networks-feed-forward-and-recurrent-neural-networks\\\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Home\",\"item\":\"https:\\\/\\\/machinelearning.humanativaspa.it\\\/en\\\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"Neural networks: feed-forward and recurrent neural networks\"}]},{\"@type\":\"WebSite\",\"@id\":\"https:\\\/\\\/machinelearning.humanativaspa.it\\\/en\\\/#website\",\"url\":\"https:\\\/\\\/machinelearning.humanativaspa.it\\\/en\\\/\",\"name\":\"HN Machine Learning\",\"description\":\"\",\"publisher\":{\"@id\":\"https:\\\/\\\/machinelearning.humanativaspa.it\\\/en\\\/#organization\"},\"alternateName\":\"Humanativa\",\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\\\/\\\/machinelearning.humanativaspa.it\\\/en\\\/?s={search_term_string}\"},\"query-input\":{\"@type\":\"PropertyValueSpecification\",\"valueRequired\":true,\"valueName\":\"search_term_string\"}}],\"inLanguage\":\"en-GB\"},{\"@type\":\"Organization\",\"@id\":\"https:\\\/\\\/machinelearning.humanativaspa.it\\\/en\\\/#organization\",\"name\":\"HN Machine Learning\",\"url\":\"https:\\\/\\\/machinelearning.humanativaspa.it\\\/en\\\/\",\"logo\":{\"@type\":\"ImageObject\",\"inLanguage\":\"en-GB\",\"@id\":\"https:\\\/\\\/machinelearning.humanativaspa.it\\\/en\\\/#\\\/schema\\\/logo\\\/image\\\/\",\"url\":\"https:\\\/\\\/machinelearning.humanativaspa.it\\\/en\\\/wp-content\\\/uploads\\\/sites\\\/4\\\/2023\\\/09\\\/libellula_hn.jpg\",\"contentUrl\":\"https:\\\/\\\/machinelearning.humanativaspa.it\\\/en\\\/wp-content\\\/uploads\\\/sites\\\/4\\\/2023\\\/09\\\/libellula_hn.jpg\",\"width\":696,\"height\":696,\"caption\":\"HN Machine Learning\"},\"image\":{\"@id\":\"https:\\\/\\\/machinelearning.humanativaspa.it\\\/en\\\/#\\\/schema\\\/logo\\\/image\\\/\"},\"sameAs\":[\"https:\\\/\\\/www.facebook.com\\\/HumanativaGroupSpA\\\/\"]},{\"@type\":\"Person\",\"@id\":\"https:\\\/\\\/machinelearning.humanativaspa.it\\\/en\\\/#\\\/schema\\\/person\\\/a6de167b6fe30bf1d2edfcbfd3417de8\",\"name\":\"Andream\",\"image\":{\"@type\":\"ImageObject\",\"inLanguage\":\"en-GB\",\"@id\":\"https:\\\/\\\/secure.gravatar.com\\\/avatar\\\/1f7a315d6f9ae9709ffc015996ad40b2c1779d16ea2dede3da3989ca3cf5aae8?s=96&d=mm&r=g\",\"url\":\"https:\\\/\\\/secure.gravatar.com\\\/avatar\\\/1f7a315d6f9ae9709ffc015996ad40b2c1779d16ea2dede3da3989ca3cf5aae8?s=96&d=mm&r=g\",\"contentUrl\":\"https:\\\/\\\/secure.gravatar.com\\\/avatar\\\/1f7a315d6f9ae9709ffc015996ad40b2c1779d16ea2dede3da3989ca3cf5aae8?s=96&d=mm&r=g\",\"caption\":\"Andream\"},\"sameAs\":[\"https:\\\/\\\/machinelearning.humanativaspa.it\\\/\"],\"url\":\"https:\\\/\\\/machinelearning.humanativaspa.it\\\/en\\\/author\\\/andream\\\/\"}]}<\/script>\n<!-- \/ Yoast SEO plugin. -->","yoast_head_json":{"title":"Neural networks: feed-forward and recurrent neural networks - HN Machine Learning en","robots":{"index":"index","follow":"follow","max-snippet":"max-snippet:-1","max-image-preview":"max-image-preview:large","max-video-preview":"max-video-preview:-1"},"canonical":"https:\/\/machinelearning.humanativaspa.it\/en\/neural-networks-feed-forward-and-recurrent-neural-networks\/","twitter_card":"summary_large_image","twitter_title":"Neural networks: feed-forward and recurrent neural networks - HN Machine Learning en","twitter_description":"Recurring models (RNNs)\u00a0\u00a0 Neural networks can be divided into two main categories: Feed-forward and Recurrent Neural Network (RNN).\u00a0 [&hellip;]","twitter_image":"https:\/\/machinelearning.humanativaspa.it\/en\/wp-content\/uploads\/sites\/4\/2023\/03\/reti_neurali_24_03_22_ist.jpg","twitter_misc":{"Written by":"Andream","Estimated reading time":"3 minutes"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"Article","@id":"https:\/\/machinelearning.humanativaspa.it\/en\/neural-networks-feed-forward-and-recurrent-neural-networks\/#article","isPartOf":{"@id":"https:\/\/machinelearning.humanativaspa.it\/en\/neural-networks-feed-forward-and-recurrent-neural-networks\/"},"author":{"name":"Andream","@id":"https:\/\/machinelearning.humanativaspa.it\/en\/#\/schema\/person\/a6de167b6fe30bf1d2edfcbfd3417de8"},"headline":"Neural networks: feed-forward and recurrent neural networks","datePublished":"2022-03-24T14:17:11+00:00","dateModified":"2023-03-03T13:58:50+00:00","mainEntityOfPage":{"@id":"https:\/\/machinelearning.humanativaspa.it\/en\/neural-networks-feed-forward-and-recurrent-neural-networks\/"},"wordCount":579,"publisher":{"@id":"https:\/\/machinelearning.humanativaspa.it\/en\/#organization"},"image":{"@id":"https:\/\/machinelearning.humanativaspa.it\/en\/neural-networks-feed-forward-and-recurrent-neural-networks\/#primaryimage"},"thumbnailUrl":"https:\/\/machinelearning.humanativaspa.it\/en\/wp-content\/uploads\/sites\/4\/2023\/03\/reti_neurali_24_03_22_ist.jpg","articleSection":["Articles"],"inLanguage":"en-GB"},{"@type":"WebPage","@id":"https:\/\/machinelearning.humanativaspa.it\/en\/neural-networks-feed-forward-and-recurrent-neural-networks\/","url":"https:\/\/machinelearning.humanativaspa.it\/en\/neural-networks-feed-forward-and-recurrent-neural-networks\/","name":"Neural networks: feed-forward and recurrent neural networks - HN Machine Learning en","isPartOf":{"@id":"https:\/\/machinelearning.humanativaspa.it\/en\/#website"},"primaryImageOfPage":{"@id":"https:\/\/machinelearning.humanativaspa.it\/en\/neural-networks-feed-forward-and-recurrent-neural-networks\/#primaryimage"},"image":{"@id":"https:\/\/machinelearning.humanativaspa.it\/en\/neural-networks-feed-forward-and-recurrent-neural-networks\/#primaryimage"},"thumbnailUrl":"https:\/\/machinelearning.humanativaspa.it\/en\/wp-content\/uploads\/sites\/4\/2023\/03\/reti_neurali_24_03_22_ist.jpg","datePublished":"2022-03-24T14:17:11+00:00","dateModified":"2023-03-03T13:58:50+00:00","breadcrumb":{"@id":"https:\/\/machinelearning.humanativaspa.it\/en\/neural-networks-feed-forward-and-recurrent-neural-networks\/#breadcrumb"},"inLanguage":"en-GB","potentialAction":[{"@type":"ReadAction","target":["https:\/\/machinelearning.humanativaspa.it\/en\/neural-networks-feed-forward-and-recurrent-neural-networks\/"]}]},{"@type":"ImageObject","inLanguage":"en-GB","@id":"https:\/\/machinelearning.humanativaspa.it\/en\/neural-networks-feed-forward-and-recurrent-neural-networks\/#primaryimage","url":"https:\/\/machinelearning.humanativaspa.it\/en\/wp-content\/uploads\/sites\/4\/2023\/03\/reti_neurali_24_03_22_ist.jpg","contentUrl":"https:\/\/machinelearning.humanativaspa.it\/en\/wp-content\/uploads\/sites\/4\/2023\/03\/reti_neurali_24_03_22_ist.jpg","width":1200,"height":600},{"@type":"BreadcrumbList","@id":"https:\/\/machinelearning.humanativaspa.it\/en\/neural-networks-feed-forward-and-recurrent-neural-networks\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https:\/\/machinelearning.humanativaspa.it\/en\/"},{"@type":"ListItem","position":2,"name":"Neural networks: feed-forward and recurrent neural networks"}]},{"@type":"WebSite","@id":"https:\/\/machinelearning.humanativaspa.it\/en\/#website","url":"https:\/\/machinelearning.humanativaspa.it\/en\/","name":"HN Machine Learning","description":"","publisher":{"@id":"https:\/\/machinelearning.humanativaspa.it\/en\/#organization"},"alternateName":"Humanativa","potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/machinelearning.humanativaspa.it\/en\/?s={search_term_string}"},"query-input":{"@type":"PropertyValueSpecification","valueRequired":true,"valueName":"search_term_string"}}],"inLanguage":"en-GB"},{"@type":"Organization","@id":"https:\/\/machinelearning.humanativaspa.it\/en\/#organization","name":"HN Machine Learning","url":"https:\/\/machinelearning.humanativaspa.it\/en\/","logo":{"@type":"ImageObject","inLanguage":"en-GB","@id":"https:\/\/machinelearning.humanativaspa.it\/en\/#\/schema\/logo\/image\/","url":"https:\/\/machinelearning.humanativaspa.it\/en\/wp-content\/uploads\/sites\/4\/2023\/09\/libellula_hn.jpg","contentUrl":"https:\/\/machinelearning.humanativaspa.it\/en\/wp-content\/uploads\/sites\/4\/2023\/09\/libellula_hn.jpg","width":696,"height":696,"caption":"HN Machine Learning"},"image":{"@id":"https:\/\/machinelearning.humanativaspa.it\/en\/#\/schema\/logo\/image\/"},"sameAs":["https:\/\/www.facebook.com\/HumanativaGroupSpA\/"]},{"@type":"Person","@id":"https:\/\/machinelearning.humanativaspa.it\/en\/#\/schema\/person\/a6de167b6fe30bf1d2edfcbfd3417de8","name":"Andream","image":{"@type":"ImageObject","inLanguage":"en-GB","@id":"https:\/\/secure.gravatar.com\/avatar\/1f7a315d6f9ae9709ffc015996ad40b2c1779d16ea2dede3da3989ca3cf5aae8?s=96&d=mm&r=g","url":"https:\/\/secure.gravatar.com\/avatar\/1f7a315d6f9ae9709ffc015996ad40b2c1779d16ea2dede3da3989ca3cf5aae8?s=96&d=mm&r=g","contentUrl":"https:\/\/secure.gravatar.com\/avatar\/1f7a315d6f9ae9709ffc015996ad40b2c1779d16ea2dede3da3989ca3cf5aae8?s=96&d=mm&r=g","caption":"Andream"},"sameAs":["https:\/\/machinelearning.humanativaspa.it\/"],"url":"https:\/\/machinelearning.humanativaspa.it\/en\/author\/andream\/"}]}},"_links":{"self":[{"href":"https:\/\/machinelearning.humanativaspa.it\/en\/wp-json\/wp\/v2\/posts\/255","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/machinelearning.humanativaspa.it\/en\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/machinelearning.humanativaspa.it\/en\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/machinelearning.humanativaspa.it\/en\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/machinelearning.humanativaspa.it\/en\/wp-json\/wp\/v2\/comments?post=255"}],"version-history":[{"count":2,"href":"https:\/\/machinelearning.humanativaspa.it\/en\/wp-json\/wp\/v2\/posts\/255\/revisions"}],"predecessor-version":[{"id":260,"href":"https:\/\/machinelearning.humanativaspa.it\/en\/wp-json\/wp\/v2\/posts\/255\/revisions\/260"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/machinelearning.humanativaspa.it\/en\/wp-json\/wp\/v2\/media\/258"}],"wp:attachment":[{"href":"https:\/\/machinelearning.humanativaspa.it\/en\/wp-json\/wp\/v2\/media?parent=255"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/machinelearning.humanativaspa.it\/en\/wp-json\/wp\/v2\/categories?post=255"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/machinelearning.humanativaspa.it\/en\/wp-json\/wp\/v2\/tags?post=255"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}