{"id":100215,"date":"2023-10-09T13:10:09","date_gmt":"2023-10-09T11:10:09","guid":{"rendered":"https:\/\/cibtestawsls.cib.de\/?p=100215"},"modified":"2024-11-04T13:35:23","modified_gmt":"2024-11-04T12:35:23","slug":"future-deep-learning-texts-images-hierarchies","status":"publish","type":"post","link":"https:\/\/cibtestawsls.cib.de\/en\/future-deep-learning-texts-images-hierarchies\/","title":{"rendered":"The Future of Deep Learning: From Texts to Images and Hierarchies\u00a0"},"content":{"rendered":"
\n\t\t\t\t\t\t
\n\t\t\t\t\t\t
\n\t\t\t\t\t
\n\t\t\t
\n\t\t\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\tYann LeCun, Chief AI Scientist at Meta AI Research and Silver Professor at the Courant Institute for Mathematical Sciences at New York University, one of the foremost minds and pioneers in the field of Deep Learning Deep Learning, gave a fascinating insight into the future of this emerging technology last Friday at the Bavarian Academy of Sciences in Munich. \t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t
\n\t\t\t\t\t\t
\n\t\t\t\t\t
\n\t\t\t
\n\t\t\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\"\"\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\t<\/div>\n\t\t<\/div>\n\t\t\t\t
\n\t\t\t
\n\t\t\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\t

His inspiring talk summarized the evolution from Deep Learning to today's large linguistic models (LLMs), such as ChatGPT, while highlighting the challenges and potentials that await us in the coming years.<\/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

\n\t\t\t\t\t\t
\n\t\t\t\t\t
\n\t\t\t
\n\t\t\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\tLeCun reduces the problem of today's large language models like ChatGPT to two main challenges. First, there is not enough text data to train the ever-growing LLMs, and text data conveys only limited \"world knowledge\" in the sense of physics. For another, LLMs are based on recursive prediction of the next word, without a planning component. LeCun therefore sees today's LLMs as an impressive breakthrough, but one that is structurally limited.\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
\n\t\t\t\t\t\t
\n\t\t\t\t\t
\n\t\t\t
\n\t\t\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t

Extension of LLMs to image data <\/h2>\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
\n\t\t\t\t\t\t
\n\t\t\t\t\t
\n\t\t\t
\n\t\t\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\tLeCun proposes to train large meshes similar to LLMs with image data by removing image regions that the mesh should then add back. \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
\n\t\t\t\t\t\t
\n\t\t\t\t\t
\n\t\t\t
\n\t\t\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\t

On the one hand, this approach solves the problem of limited text, since there is much more image data than text. On the other hand, images can easily be generated by observing the real world, while texts can only be written by humans. Similar to LLMs, Yann LeCun expects the emergence of a \"foundation model\", i.e., a model that builds emergent world knowledge about images and can be easily \"refined\" for specific applications.<\/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

\n\t\t\t\t\t\t
\n\t\t\t\t\t
\n\t\t\t
\n\t\t\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\tAmong others, Meta AI has trained and successfully \"refined\" such a model \"DINOv2\" for determining tree heights for environmental monitoring from satellite imagery with comparatively little data, demonstrating the idea of a foundation model for image data. \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
\n\t\t\t
\n\t\t\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\"\"\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\t<\/div>\n\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/section>\n\t\t\t\t
\n\t\t\t\t\t\t
\n\t\t\t\t\t
\n\t\t\t
\n\t\t\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t

Hierarchical networks for planning thinking<\/h2>\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
\n\t\t\t\t\t\t
\n\t\t\t\t\t
\n\t\t\t
\n\t\t\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\tLeCun proposes a new hierarchical architecture (H-JEPA) that allows starting with rough planning that is then progressively refined. This is intended to overcome the limitation of LLMs to think only from word to word. This idea is still in its early stages, but promises to be an exciting new direction for AI development. \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
\n\t\t\t\t\t\t
\n\t\t\t\t\t
\n\t\t\t
\n\t\t\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t

Our conclusion <\/h2>\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
\n\t\t\t\t\t\t
\n\t\t\t\t\t
\n\t\t\t
\n\t\t\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\tThe history of neural networks is a history of structural innovations, from CNN and RNN to LSTM and Transformer. LeCun's proposals could be the next evolutionary step - but there are other promising developments as well. While we eagerly await to see how his ideas evolve, one thing is certain: the integration of LLMs and image data is an important milestone. \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
\n\t\t\t\t\t\t
\n\t\t\t\t\t
\n\t\t\t
\n\t\t\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\tImage-based \"foundation networks\" could revolutionize the automatic understanding and processing of image data in business processes. However, the hardware requirements for \"foundation\" models are generally significantly higher than for specialized models. \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
\n\t\t\t\t\t\t
\n\t\t\t\t\t
\n\t\t\t
\n\t\t\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\"\"\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\t<\/div>\n\t\t<\/div>\n\t\t\t\t
\n\t\t\t
\n\t\t\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\t

With our new nVidia H100 GPUs, at CIB we are ideally positioned to track and evaluate such issues in our research department and make the most of them in our products.<\/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

\n\t\t\t\t\t\t
\n\t\t\t\t\t
\n\t\t\t
\n\t\t\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\t

Let\u00b4s CIB!<\/p>

Read more abot CIB and AI<\/a><\/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>","protected":false},"excerpt":{"rendered":"

Yann LeCun, Chief AI Scientist bei Meta AI Research und Silver Professor am Courant Institute of Mathematical Sciences der New York University, einer der f\u00fchrenden K\u00f6pfe und Pioniere auf dem Gebiet des Deep Learning, gab am vergangenen Freitag in der Bayerischen Akademie der Wissenschaften in M\u00fcnchen einen faszinierenden Ausblick auf die Zukunft dieser aufstrebenden Technologie. … Read more<\/a><\/p>","protected":false},"author":246,"featured_media":100223,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"_acf_changed":false,"footnotes":""},"categories":[922],"tags":[1826,2301],"class_list":["post-100215","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-ki-innovation","tag-ki","tag-cib-ki"],"acf":[],"yoast_head":"\nDie Zukunft von Deep Learning: Von Texten zu Bildern und Hierarchien\u00a0 - CIB Group<\/title>\n<meta name=\"description\" content=\"Yann Lecun zeigte die Herausforderungen und Potentiale auf, die uns in den kommenden Jahren in Sachen K\u00fcnstliche Intelligenz erwarten.\" \/>\n<meta name=\"robots\" content=\"noindex, follow, max-snippet:-1, max-image-preview:large, max-video-preview:-1\" \/>\n<meta property=\"og:locale\" content=\"en_GB\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"Die Zukunft von Deep Learning: Von Texten zu Bildern und Hierarchien\u00a0 - CIB Group\" \/>\n<meta property=\"og:description\" content=\"Yann Lecun zeigte die Herausforderungen und Potentiale auf, die uns in den kommenden Jahren in Sachen K\u00fcnstliche Intelligenz erwarten.\" \/>\n<meta property=\"og:url\" content=\"https:\/\/www.cib.de\/die-zukunft-von-deep-learning-von-texten-zu-bildern-und-hierarchien\/\" \/>\n<meta property=\"og:site_name\" content=\"CIB Group\" \/>\n<meta property=\"article:published_time\" content=\"2023-10-09T11:10:09+00:00\" \/>\n<meta property=\"article:modified_time\" content=\"2024-11-04T12:35:23+00:00\" \/>\n<meta property=\"og:image\" content=\"https:\/\/www.cib.de\/wp-content\/uploads\/2023\/10\/HG_blog.jpg\" \/>\n\t<meta property=\"og:image:width\" content=\"1600\" \/>\n\t<meta property=\"og:image:height\" content=\"712\" \/>\n\t<meta property=\"og:image:type\" content=\"image\/jpeg\" \/>\n<meta name=\"author\" content=\"CIB Group\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:label1\" content=\"Written by\" \/>\n\t<meta name=\"twitter:data1\" content=\"CIB Group\" \/>\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:\\\/\\\/www.cib.de\\\/die-zukunft-von-deep-learning-von-texten-zu-bildern-und-hierarchien\\\/#article\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/www.cib.de\\\/die-zukunft-von-deep-learning-von-texten-zu-bildern-und-hierarchien\\\/\"},\"author\":{\"name\":\"CIB Group\",\"@id\":\"https:\\\/\\\/cibtestawsls.cib.de\\\/#\\\/schema\\\/person\\\/4c70f0634b93acb47baacdb671694155\"},\"headline\":\"Die Zukunft von Deep Learning: Von Texten zu Bildern und Hierarchien\u00a0\",\"datePublished\":\"2023-10-09T11:10:09+00:00\",\"dateModified\":\"2024-11-04T12:35:23+00:00\",\"mainEntityOfPage\":{\"@id\":\"https:\\\/\\\/www.cib.de\\\/die-zukunft-von-deep-learning-von-texten-zu-bildern-und-hierarchien\\\/\"},\"wordCount\":521,\"image\":{\"@id\":\"https:\\\/\\\/www.cib.de\\\/die-zukunft-von-deep-learning-von-texten-zu-bildern-und-hierarchien\\\/#primaryimage\"},\"thumbnailUrl\":\"https:\\\/\\\/cibtestawsls.cib.de\\\/wp-content\\\/uploads\\\/2023\\\/10\\\/HG_blog.jpg\",\"keywords\":[\"K\u00fcnstliche Intelligenz\",\"CIB KI\"],\"articleSection\":[\"KI & Innovation\"],\"inLanguage\":\"en-GB\"},{\"@type\":\"WebPage\",\"@id\":\"https:\\\/\\\/www.cib.de\\\/die-zukunft-von-deep-learning-von-texten-zu-bildern-und-hierarchien\\\/\",\"url\":\"https:\\\/\\\/www.cib.de\\\/die-zukunft-von-deep-learning-von-texten-zu-bildern-und-hierarchien\\\/\",\"name\":\"Die Zukunft von Deep Learning: Von Texten zu Bildern und Hierarchien\u00a0 - CIB Group\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/cibtestawsls.cib.de\\\/#website\"},\"primaryImageOfPage\":{\"@id\":\"https:\\\/\\\/www.cib.de\\\/die-zukunft-von-deep-learning-von-texten-zu-bildern-und-hierarchien\\\/#primaryimage\"},\"image\":{\"@id\":\"https:\\\/\\\/www.cib.de\\\/die-zukunft-von-deep-learning-von-texten-zu-bildern-und-hierarchien\\\/#primaryimage\"},\"thumbnailUrl\":\"https:\\\/\\\/cibtestawsls.cib.de\\\/wp-content\\\/uploads\\\/2023\\\/10\\\/HG_blog.jpg\",\"datePublished\":\"2023-10-09T11:10:09+00:00\",\"dateModified\":\"2024-11-04T12:35:23+00:00\",\"author\":{\"@id\":\"https:\\\/\\\/cibtestawsls.cib.de\\\/#\\\/schema\\\/person\\\/4c70f0634b93acb47baacdb671694155\"},\"description\":\"Yann Lecun zeigte die Herausforderungen und Potentiale auf, die uns in den kommenden Jahren in Sachen K\u00fcnstliche Intelligenz erwarten.\",\"breadcrumb\":{\"@id\":\"https:\\\/\\\/www.cib.de\\\/die-zukunft-von-deep-learning-von-texten-zu-bildern-und-hierarchien\\\/#breadcrumb\"},\"inLanguage\":\"en-GB\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\\\/\\\/www.cib.de\\\/die-zukunft-von-deep-learning-von-texten-zu-bildern-und-hierarchien\\\/\"]}]},{\"@type\":\"ImageObject\",\"inLanguage\":\"en-GB\",\"@id\":\"https:\\\/\\\/www.cib.de\\\/die-zukunft-von-deep-learning-von-texten-zu-bildern-und-hierarchien\\\/#primaryimage\",\"url\":\"https:\\\/\\\/cibtestawsls.cib.de\\\/wp-content\\\/uploads\\\/2023\\\/10\\\/HG_blog.jpg\",\"contentUrl\":\"https:\\\/\\\/cibtestawsls.cib.de\\\/wp-content\\\/uploads\\\/2023\\\/10\\\/HG_blog.jpg\",\"width\":1600,\"height\":712},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\\\/\\\/www.cib.de\\\/die-zukunft-von-deep-learning-von-texten-zu-bildern-und-hierarchien\\\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Home\",\"item\":\"https:\\\/\\\/cibtestawsls.cib.de\\\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"Die Zukunft von Deep Learning: Von Texten zu Bildern und Hierarchien\u00a0\"}]},{\"@type\":\"WebSite\",\"@id\":\"https:\\\/\\\/cibtestawsls.cib.de\\\/#website\",\"url\":\"https:\\\/\\\/cibtestawsls.cib.de\\\/\",\"name\":\"CIB Group\",\"description\":\"Digitalisierung, Prozessautomatisierung, K\u00fcnstliche Intelligenz\",\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\\\/\\\/cibtestawsls.cib.de\\\/?s={search_term_string}\"},\"query-input\":{\"@type\":\"PropertyValueSpecification\",\"valueRequired\":true,\"valueName\":\"search_term_string\"}}],\"inLanguage\":\"en-GB\"},{\"@type\":\"Person\",\"@id\":\"https:\\\/\\\/cibtestawsls.cib.de\\\/#\\\/schema\\\/person\\\/4c70f0634b93acb47baacdb671694155\",\"name\":\"CIB Group\",\"image\":{\"@type\":\"ImageObject\",\"inLanguage\":\"en-GB\",\"@id\":\"https:\\\/\\\/cibtestawsls.cib.de\\\/wp-content\\\/uploads\\\/2023\\\/03\\\/logo_signature2.png\",\"url\":\"https:\\\/\\\/cibtestawsls.cib.de\\\/wp-content\\\/uploads\\\/2023\\\/03\\\/logo_signature2.png\",\"contentUrl\":\"https:\\\/\\\/cibtestawsls.cib.de\\\/wp-content\\\/uploads\\\/2023\\\/03\\\/logo_signature2.png\",\"caption\":\"CIB Group\"},\"description\":\"Die Digitalisierungsexperten\"}]}<\/script>\n<!-- \/ Yoast SEO plugin. -->","yoast_head_json":{"title":"The Future of Deep Learning: From Texts to Images and Hierarchies","description":"Yann Lecun highlighted the challenges and potentials that await us in the coming years in terms of artificial intelligence.","robots":{"index":"noindex","follow":"follow","max-snippet":"max-snippet:-1","max-image-preview":"max-image-preview:large","max-video-preview":"max-video-preview:-1"},"og_locale":"en_GB","og_type":"article","og_title":"Die Zukunft von Deep Learning: Von Texten zu Bildern und Hierarchien\u00a0 - CIB Group","og_description":"Yann Lecun zeigte die Herausforderungen und Potentiale auf, die uns in den kommenden Jahren in Sachen K\u00fcnstliche Intelligenz erwarten.","og_url":"https:\/\/www.cib.de\/die-zukunft-von-deep-learning-von-texten-zu-bildern-und-hierarchien\/","og_site_name":"CIB Group","article_published_time":"2023-10-09T11:10:09+00:00","article_modified_time":"2024-11-04T12:35:23+00:00","og_image":[{"width":1600,"height":712,"url":"https:\/\/www.cib.de\/wp-content\/uploads\/2023\/10\/HG_blog.jpg","type":"image\/jpeg"}],"author":"CIB Group","twitter_card":"summary_large_image","twitter_misc":{"Written by":"CIB Group","Estimated reading time":"3 minutes"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"Article","@id":"https:\/\/www.cib.de\/die-zukunft-von-deep-learning-von-texten-zu-bildern-und-hierarchien\/#article","isPartOf":{"@id":"https:\/\/www.cib.de\/die-zukunft-von-deep-learning-von-texten-zu-bildern-und-hierarchien\/"},"author":{"name":"CIB Group","@id":"https:\/\/cibtestawsls.cib.de\/#\/schema\/person\/4c70f0634b93acb47baacdb671694155"},"headline":"Die Zukunft von Deep Learning: Von Texten zu Bildern und Hierarchien\u00a0","datePublished":"2023-10-09T11:10:09+00:00","dateModified":"2024-11-04T12:35:23+00:00","mainEntityOfPage":{"@id":"https:\/\/www.cib.de\/die-zukunft-von-deep-learning-von-texten-zu-bildern-und-hierarchien\/"},"wordCount":521,"image":{"@id":"https:\/\/www.cib.de\/die-zukunft-von-deep-learning-von-texten-zu-bildern-und-hierarchien\/#primaryimage"},"thumbnailUrl":"https:\/\/cibtestawsls.cib.de\/wp-content\/uploads\/2023\/10\/HG_blog.jpg","keywords":["K\u00fcnstliche Intelligenz","CIB KI"],"articleSection":["KI & Innovation"],"inLanguage":"en-GB"},{"@type":"WebPage","@id":"https:\/\/www.cib.de\/die-zukunft-von-deep-learning-von-texten-zu-bildern-und-hierarchien\/","url":"https:\/\/www.cib.de\/die-zukunft-von-deep-learning-von-texten-zu-bildern-und-hierarchien\/","name":"The Future of Deep Learning: From Texts to Images and Hierarchies","isPartOf":{"@id":"https:\/\/cibtestawsls.cib.de\/#website"},"primaryImageOfPage":{"@id":"https:\/\/www.cib.de\/die-zukunft-von-deep-learning-von-texten-zu-bildern-und-hierarchien\/#primaryimage"},"image":{"@id":"https:\/\/www.cib.de\/die-zukunft-von-deep-learning-von-texten-zu-bildern-und-hierarchien\/#primaryimage"},"thumbnailUrl":"https:\/\/cibtestawsls.cib.de\/wp-content\/uploads\/2023\/10\/HG_blog.jpg","datePublished":"2023-10-09T11:10:09+00:00","dateModified":"2024-11-04T12:35:23+00:00","author":{"@id":"https:\/\/cibtestawsls.cib.de\/#\/schema\/person\/4c70f0634b93acb47baacdb671694155"},"description":"Yann Lecun highlighted the challenges and potentials that await us in the coming years in terms of artificial intelligence.","breadcrumb":{"@id":"https:\/\/www.cib.de\/die-zukunft-von-deep-learning-von-texten-zu-bildern-und-hierarchien\/#breadcrumb"},"inLanguage":"en-GB","potentialAction":[{"@type":"ReadAction","target":["https:\/\/www.cib.de\/die-zukunft-von-deep-learning-von-texten-zu-bildern-und-hierarchien\/"]}]},{"@type":"ImageObject","inLanguage":"en-GB","@id":"https:\/\/www.cib.de\/die-zukunft-von-deep-learning-von-texten-zu-bildern-und-hierarchien\/#primaryimage","url":"https:\/\/cibtestawsls.cib.de\/wp-content\/uploads\/2023\/10\/HG_blog.jpg","contentUrl":"https:\/\/cibtestawsls.cib.de\/wp-content\/uploads\/2023\/10\/HG_blog.jpg","width":1600,"height":712},{"@type":"BreadcrumbList","@id":"https:\/\/www.cib.de\/die-zukunft-von-deep-learning-von-texten-zu-bildern-und-hierarchien\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https:\/\/cibtestawsls.cib.de\/"},{"@type":"ListItem","position":2,"name":"Die Zukunft von Deep Learning: Von Texten zu Bildern und Hierarchien\u00a0"}]},{"@type":"WebSite","@id":"https:\/\/cibtestawsls.cib.de\/#website","url":"https:\/\/cibtestawsls.cib.de\/","name":"CIB Group","description":"Digitalisierung, Prozessautomatisierung, K\u00fcnstliche Intelligenz","potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/cibtestawsls.cib.de\/?s={search_term_string}"},"query-input":{"@type":"PropertyValueSpecification","valueRequired":true,"valueName":"search_term_string"}}],"inLanguage":"en-GB"},{"@type":"Person","@id":"https:\/\/cibtestawsls.cib.de\/#\/schema\/person\/4c70f0634b93acb47baacdb671694155","name":"CIB Group","image":{"@type":"ImageObject","inLanguage":"en-GB","@id":"https:\/\/cibtestawsls.cib.de\/wp-content\/uploads\/2023\/03\/logo_signature2.png","url":"https:\/\/cibtestawsls.cib.de\/wp-content\/uploads\/2023\/03\/logo_signature2.png","contentUrl":"https:\/\/cibtestawsls.cib.de\/wp-content\/uploads\/2023\/03\/logo_signature2.png","caption":"CIB Group"},"description":"Experts in digitalization"}]}},"post_mailing_queue_ids":[],"_links":{"self":[{"href":"https:\/\/cibtestawsls.cib.de\/en\/wp-json\/wp\/v2\/posts\/100215","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/cibtestawsls.cib.de\/en\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/cibtestawsls.cib.de\/en\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/cibtestawsls.cib.de\/en\/wp-json\/wp\/v2\/users\/246"}],"replies":[{"embeddable":true,"href":"https:\/\/cibtestawsls.cib.de\/en\/wp-json\/wp\/v2\/comments?post=100215"}],"version-history":[{"count":25,"href":"https:\/\/cibtestawsls.cib.de\/en\/wp-json\/wp\/v2\/posts\/100215\/revisions"}],"predecessor-version":[{"id":100262,"href":"https:\/\/cibtestawsls.cib.de\/en\/wp-json\/wp\/v2\/posts\/100215\/revisions\/100262"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/cibtestawsls.cib.de\/en\/wp-json\/wp\/v2\/media\/100223"}],"wp:attachment":[{"href":"https:\/\/cibtestawsls.cib.de\/en\/wp-json\/wp\/v2\/media?parent=100215"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/cibtestawsls.cib.de\/en\/wp-json\/wp\/v2\/categories?post=100215"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/cibtestawsls.cib.de\/en\/wp-json\/wp\/v2\/tags?post=100215"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}