{"id":4820,"date":"2022-12-07T19:29:23","date_gmt":"2022-12-08T00:29:23","guid":{"rendered":"http:\/\/skimai.com\/?p=4820"},"modified":"2024-04-29T17:27:40","modified_gmt":"2024-04-29T22:27:40","slug":"blogue-o-que-e-explicavel-ai","status":"publish","type":"post","link":"https:\/\/skimai.com\/pt\/blog-what-is-explainable-ai\/","title":{"rendered":"O que \u00e9 a IA explic\u00e1vel?"},"content":{"rendered":"<div id=\"ez-toc-container\" class=\"ez-toc-v2_0_82_1 counter-hierarchy ez-toc-counter ez-toc-grey ez-toc-container-direction\">\n<div class=\"ez-toc-title-container\">\n<p class=\"ez-toc-title\" style=\"cursor:inherit\">\u00cdndice<\/p>\n<span class=\"ez-toc-title-toggle\"><a href=\"#\" class=\"ez-toc-pull-right ez-toc-btn ez-toc-btn-xs ez-toc-btn-default ez-toc-toggle\" aria-label=\"Alternar o \u00edndice\"><span class=\"ez-toc-js-icon-con\"><span class=\"\"><span class=\"eztoc-hide\" style=\"display:none;\">Alternar<\/span><span class=\"ez-toc-icon-toggle-span\"><svg style=\"fill: #999;color:#999\" 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: #999;color:#999\" 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><\/span><\/a><\/span><\/div>\n<nav><ul class='ez-toc-list ez-toc-list-level-1' ><li class='ez-toc-page-1 ez-toc-heading-level-1'><a class=\"ez-toc-link ez-toc-heading-1\" href=\"https:\/\/skimai.com\/pt\/blog-what-is-explainable-ai\/#What_is_Explainable_AI\" >O que \u00e9 a IA explic\u00e1vel?<\/a><ul class='ez-toc-list-level-2' ><li class='ez-toc-heading-level-2'><a class=\"ez-toc-link ez-toc-heading-2\" href=\"https:\/\/skimai.com\/pt\/blog-what-is-explainable-ai\/#Use_Cases_of_Explainable_AI\" >Casos de utiliza\u00e7\u00e3o de IA explic\u00e1vel<\/a><\/li><li class='ez-toc-page-1 ez-toc-heading-level-2'><a class=\"ez-toc-link ez-toc-heading-3\" href=\"https:\/\/skimai.com\/pt\/blog-what-is-explainable-ai\/#Explainable_AI_%E2%80%93_Tools_and_Frameworks\" >IA explic\u00e1vel - Ferramentas e quadros<\/a><\/li><li class='ez-toc-page-1 ez-toc-heading-level-2'><a class=\"ez-toc-link ez-toc-heading-4\" href=\"https:\/\/skimai.com\/pt\/blog-what-is-explainable-ai\/#Conclusion\" >Conclus\u00e3o<\/a><\/li><\/ul><\/li><\/ul><\/nav><\/div>\n<h1><span class=\"ez-toc-section\" id=\"What_is_Explainable_AI\"><\/span>O que \u00e9 a IA explic\u00e1vel?<span class=\"ez-toc-section-end\"><\/span><\/h1>\n<p>Com o avan\u00e7o das tecnologias de aprendizagem profunda, como a Intelig\u00eancia Artificial (IA) e a Aprendizagem Autom\u00e1tica (AM), estamos a ser desafiados a compreender os resultados produzidos pelos algoritmos inform\u00e1ticos. Por exemplo, como \u00e9 que os algoritmos de aprendizagem autom\u00e1tica produziram um determinado resultado?<br \/>\nA IA explic\u00e1vel (ou XAI) abrange os processos e as ferramentas que permitem aos utilizadores humanos compreender os resultados gerados pelos algoritmos de ML. As organiza\u00e7\u00f5es t\u00eam de criar confian\u00e7a nos modelos de IA quando os colocam em produ\u00e7\u00e3o.<br \/>\nTodo o processo XAI \u00e9 tamb\u00e9m referido como um modelo de \"caixa negra\" que \u00e9 criado diretamente a partir dos dados gerados. De seguida, vamos analisar alguns dos casos de utiliza\u00e7\u00e3o da IA explic\u00e1vel.<\/p>\n<h2><span class=\"ez-toc-section\" id=\"Use_Cases_of_Explainable_AI\"><\/span>Casos de utiliza\u00e7\u00e3o de IA explic\u00e1vel<span class=\"ez-toc-section-end\"><\/span><\/h2>\n<p>Eis alguns dos casos de utiliza\u00e7\u00e3o real da IA explic\u00e1vel:<\/p>\n<p><strong>Para texto em linguagem natural:<\/strong><br \/>\nA XAI para Texto centra-se no desenvolvimento de modelos de caixa negra para tarefas relacionadas com texto. Por exemplo, a sumariza\u00e7\u00e3o de texto de documentos jur\u00eddicos. Neste caso de utiliza\u00e7\u00e3o, os utilizadores podem explorar e compreender o XAI for Text com base nas seguintes considera\u00e7\u00f5es:<br \/>\nTipo de tarefa centrada no texto que est\u00e1 a ser considerada<br \/>\nT\u00e9cnicas de explica\u00e7\u00e3o utilizadas para a tarefa<br \/>\nOs utilizadores-alvo da t\u00e9cnica XAI espec\u00edfica<br \/>\nDo mesmo modo, um modelo de aprendizagem profunda baseado em XAI pode classificar dados textuais sob a forma de cr\u00edticas e transcri\u00e7\u00f5es. Utilizando IA explic\u00e1vel, pode determinar por que raz\u00e3o o modelo faz previs\u00f5es com base nas palavras-chave e frases espec\u00edficas inclu\u00eddas no texto.<\/p>\n<p>Tamb\u00e9m pode utilizar o XAI para Texto para treinar um modelo de aprendizagem profunda para gerar um resumo do artigo com base no texto de origem. Por exemplo, pode obter uma distribui\u00e7\u00e3o de pontua\u00e7\u00f5es de aten\u00e7\u00e3o em tokens seleccionados no texto de origem. As palavras (com uma pontua\u00e7\u00e3o de aten\u00e7\u00e3o entre 0-1) s\u00e3o destacadas no texto de origem e apresentadas aos utilizadores finais. Quanto mais elevada for a pontua\u00e7\u00e3o de aten\u00e7\u00e3o, mais escuro ser\u00e1 o destaque do texto - e maior ser\u00e1 a import\u00e2ncia da palavra no resumo do artigo.<\/p>\n<p><strong>Para imagens visuais:<\/strong><br \/>\nA IA explic\u00e1vel \u00e9 tamb\u00e9m utilizada para automatizar a tomada de decis\u00f5es com base em imagens visuais de alta resolu\u00e7\u00e3o. Alguns exemplos de imagens de alta resolu\u00e7\u00e3o incluem imagens de sat\u00e9lite e dados m\u00e9dicos. Para al\u00e9m do elevado volume de dados de sat\u00e9lite, os dados captados s\u00e3o de alta resolu\u00e7\u00e3o e cont\u00eam v\u00e1rias bandas espectrais. Por exemplo, luz vis\u00edvel e infravermelha. \u00c9 poss\u00edvel implementar modelos treinados pela XAI para \"dividir\" imagens de alta resolu\u00e7\u00e3o em fragmentos mais pequenos.<\/p>\n<p>No dom\u00ednio das imagens m\u00e9dicas, os modelos XAI s\u00e3o utilizados para detetar pneumonia tor\u00e1cica atrav\u00e9s de radiografias. Do mesmo modo, o reconhecimento de imagens \u00e9 outro caso de utiliza\u00e7\u00e3o da IA explic\u00e1vel no dom\u00ednio das imagens visuais. Utilizando a IA visual, \u00e9 poss\u00edvel treinar modelos de IA personalizados para reconhecer imagens ou objectos (contidos em imagens capturadas).<\/p>\n<p><strong>Para estat\u00edsticas:<\/strong><br \/>\nOs modelos e algoritmos da XAI s\u00e3o eficazes com base no seu grau de exatid\u00e3o ou interpreta\u00e7\u00e3o. Os modelos de rela\u00e7\u00f5es estat\u00edsticas, como a regress\u00e3o linear, as \u00e1rvores de decis\u00e3o e a vizinhan\u00e7a mais pr\u00f3xima (K-nearest neighborhoods) s\u00e3o f\u00e1ceis de interpretar, mas menos exactos. Para que os modelos de redes neuronais sejam interpret\u00e1veis e exactos, devem ser introduzidos dados de elevada qualidade no modelo de IA.<\/p>\n<p>A XAI tem um enorme potencial no dom\u00ednio da ci\u00eancia dos dados. Por exemplo, a IA explic\u00e1vel \u00e9 utilizada nos sistemas de produ\u00e7\u00e3o estat\u00edstica da <a href=\"https:\/\/arxiv.org\/abs\/2107.08045\">Banco Central Europeu<\/a> (BCE). Ao associar os desideratos centrados no utilizador \u00e0s fun\u00e7\u00f5es \"t\u00edpicas\" do utilizador, a XAI pode delinear m\u00e9todos e t\u00e9cnicas utilizados para responder \u00e0s necessidades de cada utilizador.<\/p>\n<p>De seguida, vamos discutir as ferramentas e estruturas comuns utilizadas na IA explic\u00e1vel.<\/p>\n<h2><span class=\"ez-toc-section\" id=\"Explainable_AI_%E2%80%93_Tools_and_Frameworks\"><\/span>IA explic\u00e1vel - Ferramentas e quadros<span class=\"ez-toc-section-end\"><\/span><\/h2>\n<p>Nos \u00faltimos tempos, os investigadores de IA t\u00eam trabalhado em v\u00e1rias ferramentas e estruturas para promover a IA explic\u00e1vel. Eis algumas das mais populares:<\/p>\n<p><strong>E se:<\/strong> Desenvolvido pela equipa do TensorFlow, o What-If \u00e9 uma ferramenta visualmente interactiva utilizada para compreender o resultado dos modelos de IA do TensorFlow. Com esta ferramenta, pode visualizar facilmente conjuntos de dados juntamente com o desempenho do modelo de IA implementado.<\/p>\n<p><strong>LIME:<\/strong> Abreviatura de Local Interpretable Model-agnostic Explanation, a ferramenta LIME foi desenvolvida por uma equipa de investiga\u00e7\u00e3o da Universidade de Washington. A LIME proporciona uma melhor visibilidade sobre \"o que est\u00e1 a acontecer\" no algoritmo. Al\u00e9m disso, a LIME oferece uma forma modular e extens\u00edvel de explicar as previs\u00f5es de qualquer modelo.<\/p>\n<p><strong>AIX360:<\/strong> Desenvolvida pela IBM, a AI Explainability 360 (ou AIX 360) \u00e9 uma biblioteca de c\u00f3digo aberto utilizada para explicar e interpretar conjuntos de dados e modelos de aprendizagem autom\u00e1tica. Lan\u00e7ado como um pacote Python, o AIX360 inclui um conjunto completo de algoritmos que cobrem diferentes explica\u00e7\u00f5es juntamente com m\u00e9tricas.<\/p>\n<p><strong>SHAP:<\/strong> Abreviatura de Shapley Additive Explanations, SHAP \u00e9 uma abordagem te\u00f3rica baseada em jogos para explicar o resultado de qualquer modelo de aprendizagem autom\u00e1tica. Ao usar os valores de Shapley da teoria dos jogos, o SHAP pode conectar aloca\u00e7\u00f5es de cr\u00e9dito ideais com explica\u00e7\u00f5es locais. O SHAP \u00e9 f\u00e1cil de instalar usando PyPI ou Conda Forge.<\/p>\n<h2><span class=\"ez-toc-section\" id=\"Conclusion\"><\/span>Conclus\u00e3o<span class=\"ez-toc-section-end\"><\/span><\/h2>\n<p>As organiza\u00e7\u00f5es t\u00eam de ter uma compreens\u00e3o completa dos seus processos de tomada de decis\u00e3o baseados em IA atrav\u00e9s da monitoriza\u00e7\u00e3o da IA. A IA explic\u00e1vel permite que as organiza\u00e7\u00f5es expliquem facilmente os seus algoritmos de ML e redes neurais profundas implementados. Efetivamente, ajuda a criar confian\u00e7a nos neg\u00f3cios, juntamente com o uso produtivo de tecnologias de IA e ML.<\/p>","protected":false},"excerpt":{"rendered":"<p>What is Explainable AI? As deep learning technologies like Artificial Intelligence (AI) and Machine learning (ML) advance, we are being challenged to understand the outputs produced by computer algorithms. For example, how did ML algorithms produce a particular result? Explainable AI (or XAI) covers the processes and tools that enable human users to comprehend the [&hellip;]<\/p>\n","protected":false},"author":1003,"featured_media":4821,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"single-custom-post-template.php","format":"standard","meta":{"_et_pb_use_builder":"","_et_pb_old_content":"","_et_gb_content_width":"","footnotes":""},"categories":[125],"tags":[],"class_list":["post-4820","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-enterprise-ai-blog"],"yoast_head":"<!-- This site is optimized with the Yoast SEO plugin v24.1 - https:\/\/yoast.com\/wordpress\/plugins\/seo\/ -->\n<title>What is Explainable AI? - Skim AI<\/title>\n<meta name=\"description\" content=\"Explainable AI (or XAI) covers the processes and tools that enable human users to comprehend the outputs generated by ML algorithms.\" \/>\n<meta name=\"robots\" content=\"index, follow, max-snippet:-1, max-image-preview:large, max-video-preview:-1\" \/>\n<link rel=\"canonical\" href=\"https:\/\/skimai.com\/pt\/blogue-o-que-e-explicavel-ai\/\" \/>\n<meta property=\"og:locale\" content=\"pt_PT\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"What is Explainable AI? - Skim AI\" \/>\n<meta property=\"og:description\" content=\"Explainable AI (or XAI) covers the processes and tools that enable human users to comprehend the outputs generated by ML algorithms.\" \/>\n<meta property=\"og:url\" content=\"https:\/\/skimai.com\/pt\/blogue-o-que-e-explicavel-ai\/\" \/>\n<meta property=\"og:site_name\" content=\"Skim AI\" \/>\n<meta property=\"article:published_time\" content=\"2022-12-08T00:29:23+00:00\" \/>\n<meta property=\"article:modified_time\" content=\"2024-04-29T22:27:40+00:00\" \/>\n<meta property=\"og:image\" content=\"https:\/\/skimai.com\/wp-content\/uploads\/2022\/12\/cover8.jpg\" \/>\n\t<meta property=\"og:image:width\" content=\"960\" \/>\n\t<meta property=\"og:image:height\" content=\"640\" \/>\n\t<meta property=\"og:image:type\" content=\"image\/jpeg\" \/>\n<meta name=\"author\" content=\"Greggory Elias\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:label1\" content=\"Escrito por\" \/>\n\t<meta name=\"twitter:data1\" content=\"Greggory Elias\" \/>\n\t<meta name=\"twitter:label2\" content=\"Tempo estimado de leitura\" \/>\n\t<meta name=\"twitter:data2\" content=\"4 minutos\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\/\/schema.org\",\"@graph\":[{\"@type\":\"Article\",\"@id\":\"https:\/\/skimai.com\/blog-what-is-explainable-ai\/#article\",\"isPartOf\":{\"@id\":\"https:\/\/skimai.com\/blog-what-is-explainable-ai\/\"},\"author\":{\"name\":\"Greggory Elias\",\"@id\":\"https:\/\/skimai.com\/uk\/#\/schema\/person\/7a883b4a2d2ea22040f42a7975eb86c6\"},\"headline\":\"What is Explainable AI?\",\"datePublished\":\"2022-12-08T00:29:23+00:00\",\"dateModified\":\"2024-04-29T22:27:40+00:00\",\"mainEntityOfPage\":{\"@id\":\"https:\/\/skimai.com\/blog-what-is-explainable-ai\/\"},\"wordCount\":784,\"publisher\":{\"@id\":\"https:\/\/skimai.com\/uk\/#organization\"},\"image\":{\"@id\":\"https:\/\/skimai.com\/blog-what-is-explainable-ai\/#primaryimage\"},\"thumbnailUrl\":\"https:\/\/skimai.com\/wp-content\/uploads\/2022\/12\/cover8.jpg\",\"articleSection\":[\"Enterprise AI\"],\"inLanguage\":\"pt-PT\"},{\"@type\":\"WebPage\",\"@id\":\"https:\/\/skimai.com\/blog-what-is-explainable-ai\/\",\"url\":\"https:\/\/skimai.com\/blog-what-is-explainable-ai\/\",\"name\":\"What is Explainable AI? - Skim AI\",\"isPartOf\":{\"@id\":\"https:\/\/skimai.com\/uk\/#website\"},\"primaryImageOfPage\":{\"@id\":\"https:\/\/skimai.com\/blog-what-is-explainable-ai\/#primaryimage\"},\"image\":{\"@id\":\"https:\/\/skimai.com\/blog-what-is-explainable-ai\/#primaryimage\"},\"thumbnailUrl\":\"https:\/\/skimai.com\/wp-content\/uploads\/2022\/12\/cover8.jpg\",\"datePublished\":\"2022-12-08T00:29:23+00:00\",\"dateModified\":\"2024-04-29T22:27:40+00:00\",\"description\":\"Explainable AI (or XAI) covers the processes and tools that enable human users to comprehend the outputs generated by ML algorithms.\",\"breadcrumb\":{\"@id\":\"https:\/\/skimai.com\/blog-what-is-explainable-ai\/#breadcrumb\"},\"inLanguage\":\"pt-PT\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\/\/skimai.com\/blog-what-is-explainable-ai\/\"]}]},{\"@type\":\"ImageObject\",\"inLanguage\":\"pt-PT\",\"@id\":\"https:\/\/skimai.com\/blog-what-is-explainable-ai\/#primaryimage\",\"url\":\"https:\/\/skimai.com\/wp-content\/uploads\/2022\/12\/cover8.jpg\",\"contentUrl\":\"https:\/\/skimai.com\/wp-content\/uploads\/2022\/12\/cover8.jpg\",\"width\":960,\"height\":640,\"caption\":\"cover8\"},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\/\/skimai.com\/blog-what-is-explainable-ai\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Home\",\"item\":\"https:\/\/skimai.com\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"What is Explainable AI?\"}]},{\"@type\":\"WebSite\",\"@id\":\"https:\/\/skimai.com\/uk\/#website\",\"url\":\"https:\/\/skimai.com\/uk\/\",\"name\":\"Skim AI\",\"description\":\"The AI Agent Workforce Platform\",\"publisher\":{\"@id\":\"https:\/\/skimai.com\/uk\/#organization\"},\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\/\/skimai.com\/uk\/?s={search_term_string}\"},\"query-input\":{\"@type\":\"PropertyValueSpecification\",\"valueRequired\":true,\"valueName\":\"search_term_string\"}}],\"inLanguage\":\"pt-PT\"},{\"@type\":\"Organization\",\"@id\":\"https:\/\/skimai.com\/uk\/#organization\",\"name\":\"Skim AI\",\"url\":\"https:\/\/skimai.com\/uk\/\",\"logo\":{\"@type\":\"ImageObject\",\"inLanguage\":\"pt-PT\",\"@id\":\"https:\/\/skimai.com\/uk\/#\/schema\/logo\/image\/\",\"url\":\"http:\/\/skimai.com\/wp-content\/uploads\/2020\/07\/SKIM-AI-Header-Logo.png\",\"contentUrl\":\"http:\/\/skimai.com\/wp-content\/uploads\/2020\/07\/SKIM-AI-Header-Logo.png\",\"width\":194,\"height\":58,\"caption\":\"Skim AI\"},\"image\":{\"@id\":\"https:\/\/skimai.com\/uk\/#\/schema\/logo\/image\/\"},\"sameAs\":[\"https:\/\/www.linkedin.com\/company\/skim-ai\"]},{\"@type\":\"Person\",\"@id\":\"https:\/\/skimai.com\/uk\/#\/schema\/person\/7a883b4a2d2ea22040f42a7975eb86c6\",\"name\":\"Greggory Elias\",\"url\":\"https:\/\/skimai.com\/pt\/author\/gregg\/\"}]}<\/script>\n<!-- \/ Yoast SEO plugin. -->","yoast_head_json":{"title":"O que \u00e9 a IA explic\u00e1vel? - IA de esguelha","description":"A IA explic\u00e1vel (ou XAI) abrange os processos e ferramentas que permitem aos utilizadores humanos compreender os resultados gerados pelos algoritmos de aprendizagem autom\u00e1tica.","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:\/\/skimai.com\/pt\/blogue-o-que-e-explicavel-ai\/","og_locale":"pt_PT","og_type":"article","og_title":"What is Explainable AI? - Skim AI","og_description":"Explainable AI (or XAI) covers the processes and tools that enable human users to comprehend the outputs generated by ML algorithms.","og_url":"https:\/\/skimai.com\/pt\/blogue-o-que-e-explicavel-ai\/","og_site_name":"Skim AI","article_published_time":"2022-12-08T00:29:23+00:00","article_modified_time":"2024-04-29T22:27:40+00:00","og_image":[{"width":960,"height":640,"url":"https:\/\/skimai.com\/wp-content\/uploads\/2022\/12\/cover8.jpg","type":"image\/jpeg"}],"author":"Greggory Elias","twitter_card":"summary_large_image","twitter_misc":{"Escrito por":"Greggory Elias","Tempo estimado de leitura":"4 minutos"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"Article","@id":"https:\/\/skimai.com\/blog-what-is-explainable-ai\/#article","isPartOf":{"@id":"https:\/\/skimai.com\/blog-what-is-explainable-ai\/"},"author":{"name":"Greggory Elias","@id":"https:\/\/skimai.com\/uk\/#\/schema\/person\/7a883b4a2d2ea22040f42a7975eb86c6"},"headline":"What is Explainable AI?","datePublished":"2022-12-08T00:29:23+00:00","dateModified":"2024-04-29T22:27:40+00:00","mainEntityOfPage":{"@id":"https:\/\/skimai.com\/blog-what-is-explainable-ai\/"},"wordCount":784,"publisher":{"@id":"https:\/\/skimai.com\/uk\/#organization"},"image":{"@id":"https:\/\/skimai.com\/blog-what-is-explainable-ai\/#primaryimage"},"thumbnailUrl":"https:\/\/skimai.com\/wp-content\/uploads\/2022\/12\/cover8.jpg","articleSection":["Enterprise AI"],"inLanguage":"pt-PT"},{"@type":"WebPage","@id":"https:\/\/skimai.com\/blog-what-is-explainable-ai\/","url":"https:\/\/skimai.com\/blog-what-is-explainable-ai\/","name":"O que \u00e9 a IA explic\u00e1vel? - IA de esguelha","isPartOf":{"@id":"https:\/\/skimai.com\/uk\/#website"},"primaryImageOfPage":{"@id":"https:\/\/skimai.com\/blog-what-is-explainable-ai\/#primaryimage"},"image":{"@id":"https:\/\/skimai.com\/blog-what-is-explainable-ai\/#primaryimage"},"thumbnailUrl":"https:\/\/skimai.com\/wp-content\/uploads\/2022\/12\/cover8.jpg","datePublished":"2022-12-08T00:29:23+00:00","dateModified":"2024-04-29T22:27:40+00:00","description":"A IA explic\u00e1vel (ou XAI) abrange os processos e ferramentas que permitem aos utilizadores humanos compreender os resultados gerados pelos algoritmos de aprendizagem autom\u00e1tica.","breadcrumb":{"@id":"https:\/\/skimai.com\/blog-what-is-explainable-ai\/#breadcrumb"},"inLanguage":"pt-PT","potentialAction":[{"@type":"ReadAction","target":["https:\/\/skimai.com\/blog-what-is-explainable-ai\/"]}]},{"@type":"ImageObject","inLanguage":"pt-PT","@id":"https:\/\/skimai.com\/blog-what-is-explainable-ai\/#primaryimage","url":"https:\/\/skimai.com\/wp-content\/uploads\/2022\/12\/cover8.jpg","contentUrl":"https:\/\/skimai.com\/wp-content\/uploads\/2022\/12\/cover8.jpg","width":960,"height":640,"caption":"cover8"},{"@type":"BreadcrumbList","@id":"https:\/\/skimai.com\/blog-what-is-explainable-ai\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https:\/\/skimai.com\/"},{"@type":"ListItem","position":2,"name":"What is Explainable AI?"}]},{"@type":"WebSite","@id":"https:\/\/skimai.com\/uk\/#website","url":"https:\/\/skimai.com\/uk\/","name":"IA de desnata\u00e7\u00e3o","description":"A plataforma de for\u00e7a de trabalho de agentes de IA","publisher":{"@id":"https:\/\/skimai.com\/uk\/#organization"},"potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/skimai.com\/uk\/?s={search_term_string}"},"query-input":{"@type":"PropertyValueSpecification","valueRequired":true,"valueName":"search_term_string"}}],"inLanguage":"pt-PT"},{"@type":"Organization","@id":"https:\/\/skimai.com\/uk\/#organization","name":"IA de desnata\u00e7\u00e3o","url":"https:\/\/skimai.com\/uk\/","logo":{"@type":"ImageObject","inLanguage":"pt-PT","@id":"https:\/\/skimai.com\/uk\/#\/schema\/logo\/image\/","url":"http:\/\/skimai.com\/wp-content\/uploads\/2020\/07\/SKIM-AI-Header-Logo.png","contentUrl":"http:\/\/skimai.com\/wp-content\/uploads\/2020\/07\/SKIM-AI-Header-Logo.png","width":194,"height":58,"caption":"Skim AI"},"image":{"@id":"https:\/\/skimai.com\/uk\/#\/schema\/logo\/image\/"},"sameAs":["https:\/\/www.linkedin.com\/company\/skim-ai"]},{"@type":"Person","@id":"https:\/\/skimai.com\/uk\/#\/schema\/person\/7a883b4a2d2ea22040f42a7975eb86c6","name":"Greggory Elias","url":"https:\/\/skimai.com\/pt\/author\/gregg\/"}]}},"_links":{"self":[{"href":"https:\/\/skimai.com\/pt\/wp-json\/wp\/v2\/posts\/4820","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/skimai.com\/pt\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/skimai.com\/pt\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/skimai.com\/pt\/wp-json\/wp\/v2\/users\/1003"}],"replies":[{"embeddable":true,"href":"https:\/\/skimai.com\/pt\/wp-json\/wp\/v2\/comments?post=4820"}],"version-history":[{"count":0,"href":"https:\/\/skimai.com\/pt\/wp-json\/wp\/v2\/posts\/4820\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/skimai.com\/pt\/wp-json\/wp\/v2\/media\/4821"}],"wp:attachment":[{"href":"https:\/\/skimai.com\/pt\/wp-json\/wp\/v2\/media?parent=4820"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/skimai.com\/pt\/wp-json\/wp\/v2\/categories?post=4820"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/skimai.com\/pt\/wp-json\/wp\/v2\/tags?post=4820"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}