{"id":8866,"date":"2026-06-06T16:04:36","date_gmt":"2026-06-06T08:04:36","guid":{"rendered":"https:\/\/infernews.com\/blog\/?page_id=8866"},"modified":"2026-06-06T16:11:27","modified_gmt":"2026-06-06T08:11:27","slug":"deep-learning-%e6%b7%b1%e5%ba%a6%e5%ad%b8%e7%bf%92","status":"publish","type":"page","link":"https:\/\/infernews.com\/blog\/deep-learning-%e6%b7%b1%e5%ba%a6%e5%ad%b8%e7%bf%92\/","title":{"rendered":"Deep Learning \u6df1\u5ea6\u5b78\u7fd2"},"content":{"rendered":"<figure class=\"wp-block-embed-youtube wp-block-embed is-type-video is-provider-youtube wp-embed-aspect-16-9 wp-has-aspect-ratio\"><div class=\"lyte-wrapper\" title=\"1: Introduction to Neural Networks and Deep Learning; Training Deep NNs\" style=\"width:853px;max-width:100%;margin:5px auto;\"><div class=\"lyMe\" id=\"WYL_kyQ0CRkYhy4\" itemprop=\"video\" itemscope itemtype=\"https:\/\/schema.org\/VideoObject\"><div><meta itemprop=\"thumbnailUrl\" content=\"https:\/\/infernews.com\/blog\/wp-content\/plugins\/wp-youtube-lyte\/lyteCache.php?origThumbUrl=https%3A%2F%2Fi.ytimg.com%2Fvi%2FkyQ0CRkYhy4%2Fhqdefault.jpg\" \/><meta itemprop=\"embedURL\" content=\"https:\/\/www.youtube.com\/embed\/kyQ0CRkYhy4\" \/><meta itemprop=\"duration\" content=\"PT57M5S\" \/><meta itemprop=\"uploadDate\" content=\"2026-01-07T15:01:30Z\" \/><\/div><meta itemprop=\"accessibilityFeature\" content=\"captions\" \/><div id=\"lyte_kyQ0CRkYhy4\" data-src=\"https:\/\/infernews.com\/blog\/wp-content\/plugins\/wp-youtube-lyte\/lyteCache.php?origThumbUrl=https%3A%2F%2Fi.ytimg.com%2Fvi%2FkyQ0CRkYhy4%2Fhqdefault.jpg\" class=\"pL\"><div class=\"tC\"><div class=\"tT\" itemprop=\"name\">1: Introduction to Neural Networks and Deep Learning; Training Deep NNs<\/div><\/div><div class=\"play\"><\/div><div class=\"ctrl\"><div class=\"Lctrl\"><\/div><div class=\"Rctrl\"><\/div><\/div><\/div><noscript><a href=\"https:\/\/youtu.be\/kyQ0CRkYhy4\" rel=\"nofollow noopener\"><img loading=\"lazy\" decoding=\"async\" src=\"https:\/\/infernews.com\/blog\/wp-content\/plugins\/wp-youtube-lyte\/lyteCache.php?origThumbUrl=https%3A%2F%2Fi.ytimg.com%2Fvi%2FkyQ0CRkYhy4%2F0.jpg\" alt=\"1: Introduction to Neural Networks and Deep Learning; Training Deep NNs\" width=\"853\" height=\"460\" \/><br \/>Watch this video on YouTube<\/a><\/noscript><meta itemprop=\"description\" content=\"MIT 15.773 Hands-On Deep Learning Spring 2024 Instructor: Rama Ramakrishnan View the complete course: https:\/\/ocw.mit.edu\/courses\/15-773-hands-on-deep-learning-spring-2024 YouTube Playlist: https:\/\/www.youtube.com\/playlist?list=PLUl4u3cNGP60YyhMjYmXuVmX562QcClSp Introduction and overview of the course covering the history and background of the field. License: Creative Commons BY-NC-SAMore information at https:\/\/ocw.mit.edu\/termsMore courses at https:\/\/ocw.mit.eduSupport OCW at http:\/\/ow.ly\/a1If50zVRlQ We encourage constructive comments and discussion on OCW\u2019s YouTube and other social media channels. Personal attacks, hate speech, trolling, and inappropriate comments are not allowed and may be removed. More details at https:\/\/ocw.mit.edu\/comments.\"><\/div><\/div><div class=\"lL\" style=\"max-width:100%;width:853px;margin:5px auto;\"><\/div><figcaption><\/figcaption><\/figure>\n<figure class=\"wp-block-embed-youtube wp-block-embed is-type-video is-provider-youtube wp-embed-aspect-16-9 wp-has-aspect-ratio\"><div class=\"lyte-wrapper\" title=\"2: Training Deep NNs (cont.); Introduction to Keras\/Tensorflow; Application to Tabular Data\" style=\"width:853px;max-width:100%;margin:5px auto;\"><div class=\"lyMe\" id=\"WYL_3Lr8nVUDCpk\" itemprop=\"video\" itemscope itemtype=\"https:\/\/schema.org\/VideoObject\"><div><meta itemprop=\"thumbnailUrl\" content=\"https:\/\/infernews.com\/blog\/wp-content\/plugins\/wp-youtube-lyte\/lyteCache.php?origThumbUrl=https%3A%2F%2Fi.ytimg.com%2Fvi%2F3Lr8nVUDCpk%2Fhqdefault.jpg\" \/><meta itemprop=\"embedURL\" content=\"https:\/\/www.youtube.com\/embed\/3Lr8nVUDCpk\" \/><meta itemprop=\"duration\" content=\"PT1H18M22S\" \/><meta itemprop=\"uploadDate\" content=\"2026-01-07T15:01:40Z\" \/><\/div><meta itemprop=\"accessibilityFeature\" content=\"captions\" \/><div id=\"lyte_3Lr8nVUDCpk\" data-src=\"https:\/\/infernews.com\/blog\/wp-content\/plugins\/wp-youtube-lyte\/lyteCache.php?origThumbUrl=https%3A%2F%2Fi.ytimg.com%2Fvi%2F3Lr8nVUDCpk%2Fhqdefault.jpg\" class=\"pL\"><div class=\"tC\"><div class=\"tT\" itemprop=\"name\">2: Training Deep NNs (cont.); Introduction to Keras\/Tensorflow; Application to Tabular Data<\/div><\/div><div class=\"play\"><\/div><div class=\"ctrl\"><div class=\"Lctrl\"><\/div><div class=\"Rctrl\"><\/div><\/div><\/div><noscript><a href=\"https:\/\/youtu.be\/3Lr8nVUDCpk\" rel=\"nofollow noopener\"><img loading=\"lazy\" decoding=\"async\" src=\"https:\/\/infernews.com\/blog\/wp-content\/plugins\/wp-youtube-lyte\/lyteCache.php?origThumbUrl=https%3A%2F%2Fi.ytimg.com%2Fvi%2F3Lr8nVUDCpk%2F0.jpg\" alt=\"2: Training Deep NNs (cont.); Introduction to Keras\/Tensorflow; Application to Tabular Data\" width=\"853\" height=\"460\" \/><br \/>Watch this video on YouTube<\/a><\/noscript><meta itemprop=\"description\" content=\"MIT 15.773 Hands-On Deep Learning Spring 2024 Instructor: Rama Ramakrishnan View the complete course: https:\/\/ocw.mit.edu\/courses\/15-773-hands-on-deep-learning-spring-2024 YouTube Playlist: https:\/\/www.youtube.com\/playlist?list=PLUl4u3cNGP60YyhMjYmXuVmX562QcClSp This session introduces various aspects of designing and training deep neural networks using the example of a model for heart disease prediction. License: Creative Commons BY-NC-SAMore information at https:\/\/ocw.mit.edu\/termsMore courses at https:\/\/ocw.mit.eduSupport OCW at http:\/\/ow.ly\/a1If50zVRlQ We encourage constructive comments and discussion on OCW\u2019s YouTube and other social media channels. Personal attacks, hate speech, trolling, and inappropriate comments are not allowed and may be removed. More details at https:\/\/ocw.mit.edu\/comments.\"><\/div><\/div><div class=\"lL\" style=\"max-width:100%;width:853px;margin:5px auto;\"><\/div><figcaption><\/figcaption><\/figure>\n<figure class=\"wp-block-embed-youtube wp-block-embed is-type-video is-provider-youtube wp-embed-aspect-16-9 wp-has-aspect-ratio\"><div class=\"lyte-wrapper\" title=\"3: Deep Learning for Computer Vision &ndash; Building Convolutional Neural Networks from Scratch\" style=\"width:853px;max-width:100%;margin:5px auto;\"><div class=\"lyMe\" id=\"WYL_8QuyDcMIdRc\" itemprop=\"video\" itemscope itemtype=\"https:\/\/schema.org\/VideoObject\"><div><meta itemprop=\"thumbnailUrl\" content=\"https:\/\/infernews.com\/blog\/wp-content\/plugins\/wp-youtube-lyte\/lyteCache.php?origThumbUrl=https%3A%2F%2Fi.ytimg.com%2Fvi%2F8QuyDcMIdRc%2Fhqdefault.jpg\" \/><meta itemprop=\"embedURL\" content=\"https:\/\/www.youtube.com\/embed\/8QuyDcMIdRc\" \/><meta itemprop=\"duration\" content=\"PT1H17M13S\" \/><meta itemprop=\"uploadDate\" content=\"2026-01-07T15:01:49Z\" \/><\/div><meta itemprop=\"accessibilityFeature\" content=\"captions\" \/><div id=\"lyte_8QuyDcMIdRc\" data-src=\"https:\/\/infernews.com\/blog\/wp-content\/plugins\/wp-youtube-lyte\/lyteCache.php?origThumbUrl=https%3A%2F%2Fi.ytimg.com%2Fvi%2F8QuyDcMIdRc%2Fhqdefault.jpg\" class=\"pL\"><div class=\"tC\"><div class=\"tT\" itemprop=\"name\">3: Deep Learning for Computer Vision \u2013 Building Convolutional Neural Networks from Scratch<\/div><\/div><div class=\"play\"><\/div><div class=\"ctrl\"><div class=\"Lctrl\"><\/div><div class=\"Rctrl\"><\/div><\/div><\/div><noscript><a href=\"https:\/\/youtu.be\/8QuyDcMIdRc\" rel=\"nofollow noopener\"><img loading=\"lazy\" decoding=\"async\" src=\"https:\/\/infernews.com\/blog\/wp-content\/plugins\/wp-youtube-lyte\/lyteCache.php?origThumbUrl=https%3A%2F%2Fi.ytimg.com%2Fvi%2F8QuyDcMIdRc%2F0.jpg\" alt=\"3: Deep Learning for Computer Vision &ndash; Building Convolutional Neural Networks from Scratch\" width=\"853\" height=\"460\" \/><br \/>Watch this video on YouTube<\/a><\/noscript><meta itemprop=\"description\" content=\"MIT 15.773 Hands-On Deep Learning Spring 2024 Instructor: Rama Ramakrishnan View the complete course: https:\/\/ocw.mit.edu\/courses\/15-773-hands-on-deep-learning-spring-2024 YouTube Playlist: https:\/\/www.youtube.com\/playlist?list=PLUl4u3cNGP60YyhMjYmXuVmX562QcClSp A recap of training flow is given, then the rest of the session walks through the steps of building a deep neural network in Colab. License: Creative Commons BY-NC-SAMore information at https:\/\/ocw.mit.edu\/termsMore courses at https:\/\/ocw.mit.eduSupport OCW at http:\/\/ow.ly\/a1If50zVRlQ We encourage constructive comments and discussion on OCW\u2019s YouTube and other social media channels. Personal attacks, hate speech, trolling, and inappropriate comments are not allowed and may be removed. More details at https:\/\/ocw.mit.edu\/comments.\"><\/div><\/div><div class=\"lL\" style=\"max-width:100%;width:853px;margin:5px auto;\"><\/div><figcaption><\/figcaption><\/figure>\n<figure class=\"wp-block-embed-youtube wp-block-embed is-type-video is-provider-youtube wp-embed-aspect-16-9 wp-has-aspect-ratio\"><div class=\"lyte-wrapper\" title=\"4: Deep Learning for Computer Vision &ndash; Transfer Learning and Fine-Tuning; Intro to HuggingFace\" style=\"width:853px;max-width:100%;margin:5px auto;\"><div class=\"lyMe\" id=\"WYL_8xh7Y0pBrCE\" itemprop=\"video\" itemscope itemtype=\"https:\/\/schema.org\/VideoObject\"><div><meta itemprop=\"thumbnailUrl\" content=\"https:\/\/infernews.com\/blog\/wp-content\/plugins\/wp-youtube-lyte\/lyteCache.php?origThumbUrl=https%3A%2F%2Fi.ytimg.com%2Fvi%2F8xh7Y0pBrCE%2Fhqdefault.jpg\" \/><meta itemprop=\"embedURL\" content=\"https:\/\/www.youtube.com\/embed\/8xh7Y0pBrCE\" \/><meta itemprop=\"duration\" content=\"PT1H16M22S\" \/><meta itemprop=\"uploadDate\" content=\"2026-01-07T15:01:38Z\" \/><\/div><meta itemprop=\"accessibilityFeature\" content=\"captions\" \/><div id=\"lyte_8xh7Y0pBrCE\" data-src=\"https:\/\/infernews.com\/blog\/wp-content\/plugins\/wp-youtube-lyte\/lyteCache.php?origThumbUrl=https%3A%2F%2Fi.ytimg.com%2Fvi%2F8xh7Y0pBrCE%2Fhqdefault.jpg\" class=\"pL\"><div class=\"tC\"><div class=\"tT\" itemprop=\"name\">4: Deep Learning for Computer Vision \u2013 Transfer Learning and Fine-Tuning; Intro to HuggingFace<\/div><\/div><div class=\"play\"><\/div><div class=\"ctrl\"><div class=\"Lctrl\"><\/div><div class=\"Rctrl\"><\/div><\/div><\/div><noscript><a href=\"https:\/\/youtu.be\/8xh7Y0pBrCE\" rel=\"nofollow noopener\"><img loading=\"lazy\" decoding=\"async\" src=\"https:\/\/infernews.com\/blog\/wp-content\/plugins\/wp-youtube-lyte\/lyteCache.php?origThumbUrl=https%3A%2F%2Fi.ytimg.com%2Fvi%2F8xh7Y0pBrCE%2F0.jpg\" alt=\"4: Deep Learning for Computer Vision &ndash; Transfer Learning and Fine-Tuning; Intro to HuggingFace\" width=\"853\" height=\"460\" \/><br \/>Watch this video on YouTube<\/a><\/noscript><meta itemprop=\"description\" content=\"MIT 15.773 Hands-On Deep Learning Spring 2024 Instructor: Rama Ramakrishnan View the complete course: https:\/\/ocw.mit.edu\/courses\/15-773-hands-on-deep-learning-spring-2024 YouTube Playlist: https:\/\/www.youtube.com\/playlist?list=PLUl4u3cNGP60YyhMjYmXuVmX562QcClSp Covers transfer learning, convolutional neural network (CNN) models, pooling layers, and application examples, including a handbags-shoes classifier. License: Creative Commons BY-NC-SAMore information at https:\/\/ocw.mit.edu\/termsMore courses at https:\/\/ocw.mit.eduSupport OCW at http:\/\/ow.ly\/a1If50zVRlQ We encourage constructive comments and discussion on OCW\u2019s YouTube and other social media channels. Personal attacks, hate speech, trolling, and inappropriate comments are not allowed and may be removed. More details at https:\/\/ocw.mit.edu\/comments.\"><\/div><\/div><div class=\"lL\" style=\"max-width:100%;width:853px;margin:5px auto;\"><\/div><figcaption><\/figcaption><\/figure>\n<figure class=\"wp-block-embed-youtube wp-block-embed is-type-video is-provider-youtube wp-embed-aspect-16-9 wp-has-aspect-ratio\"><div class=\"lyte-wrapper\" title=\"5: Deep Learning for Natural Language &ndash; The Basics\" style=\"width:853px;max-width:100%;margin:5px auto;\"><div class=\"lyMe\" id=\"WYL_duBLxHjaecQ\" itemprop=\"video\" itemscope itemtype=\"https:\/\/schema.org\/VideoObject\"><div><meta itemprop=\"thumbnailUrl\" content=\"https:\/\/infernews.com\/blog\/wp-content\/plugins\/wp-youtube-lyte\/lyteCache.php?origThumbUrl=https%3A%2F%2Fi.ytimg.com%2Fvi%2FduBLxHjaecQ%2Fhqdefault.jpg\" \/><meta itemprop=\"embedURL\" content=\"https:\/\/www.youtube.com\/embed\/duBLxHjaecQ\" \/><meta itemprop=\"duration\" content=\"PT1H17M4S\" \/><meta itemprop=\"uploadDate\" content=\"2026-01-07T15:01:42Z\" \/><\/div><meta itemprop=\"accessibilityFeature\" content=\"captions\" \/><div id=\"lyte_duBLxHjaecQ\" data-src=\"https:\/\/infernews.com\/blog\/wp-content\/plugins\/wp-youtube-lyte\/lyteCache.php?origThumbUrl=https%3A%2F%2Fi.ytimg.com%2Fvi%2FduBLxHjaecQ%2Fhqdefault.jpg\" class=\"pL\"><div class=\"tC\"><div class=\"tT\" itemprop=\"name\">5: Deep Learning for Natural Language \u2013 The Basics<\/div><\/div><div class=\"play\"><\/div><div class=\"ctrl\"><div class=\"Lctrl\"><\/div><div class=\"Rctrl\"><\/div><\/div><\/div><noscript><a href=\"https:\/\/youtu.be\/duBLxHjaecQ\" rel=\"nofollow noopener\"><img loading=\"lazy\" decoding=\"async\" src=\"https:\/\/infernews.com\/blog\/wp-content\/plugins\/wp-youtube-lyte\/lyteCache.php?origThumbUrl=https%3A%2F%2Fi.ytimg.com%2Fvi%2FduBLxHjaecQ%2F0.jpg\" alt=\"5: Deep Learning for Natural Language &ndash; The Basics\" width=\"853\" height=\"460\" \/><br \/>Watch this video on YouTube<\/a><\/noscript><meta itemprop=\"description\" content=\"MIT 15.773 Hands-On Deep Learning Spring 2024 Instructor: Rama Ramakrishnan View the complete course: https:\/\/ocw.mit.edu\/courses\/15-773-hands-on-deep-learning-spring-2024 YouTube Playlist: https:\/\/www.youtube.com\/playlist?list=PLUl4u3cNGP60YyhMjYmXuVmX562QcClSp Introduction to natural language processing, including vectorization, the bag-of-words model, and includes demonstration in CoLab. License: Creative Commons BY-NC-SAMore information at https:\/\/ocw.mit.edu\/termsMore courses at https:\/\/ocw.mit.eduSupport OCW at http:\/\/ow.ly\/a1If50zVRlQ We encourage constructive comments and discussion on OCW\u2019s YouTube and other social media channels. Personal attacks, hate speech, trolling, and inappropriate comments are not allowed and may be removed. More details at https:\/\/ocw.mit.edu\/comments.\"><\/div><\/div><div class=\"lL\" style=\"max-width:100%;width:853px;margin:5px auto;\"><\/div><figcaption><\/figcaption><\/figure>\n<figure class=\"wp-block-embed-youtube wp-block-embed is-type-video is-provider-youtube wp-embed-aspect-16-9 wp-has-aspect-ratio\"><div class=\"lyte-wrapper\" title=\"6: Deep Learning for Natural Language &ndash; Embeddings\" style=\"width:853px;max-width:100%;margin:5px auto;\"><div class=\"lyMe\" id=\"WYL_LqFc0z-pQTg\" itemprop=\"video\" itemscope itemtype=\"https:\/\/schema.org\/VideoObject\"><div><meta itemprop=\"thumbnailUrl\" content=\"https:\/\/infernews.com\/blog\/wp-content\/plugins\/wp-youtube-lyte\/lyteCache.php?origThumbUrl=https%3A%2F%2Fi.ytimg.com%2Fvi%2FLqFc0z-pQTg%2Fhqdefault.jpg\" \/><meta itemprop=\"embedURL\" content=\"https:\/\/www.youtube.com\/embed\/LqFc0z-pQTg\" \/><meta itemprop=\"duration\" content=\"PT1H17M51S\" \/><meta itemprop=\"uploadDate\" content=\"2026-01-07T15:01:36Z\" \/><\/div><meta itemprop=\"accessibilityFeature\" content=\"captions\" \/><div id=\"lyte_LqFc0z-pQTg\" data-src=\"https:\/\/infernews.com\/blog\/wp-content\/plugins\/wp-youtube-lyte\/lyteCache.php?origThumbUrl=https%3A%2F%2Fi.ytimg.com%2Fvi%2FLqFc0z-pQTg%2Fhqdefault.jpg\" class=\"pL\"><div class=\"tC\"><div class=\"tT\" itemprop=\"name\">6: Deep Learning for Natural Language \u2013 Embeddings<\/div><\/div><div class=\"play\"><\/div><div class=\"ctrl\"><div class=\"Lctrl\"><\/div><div class=\"Rctrl\"><\/div><\/div><\/div><noscript><a href=\"https:\/\/youtu.be\/LqFc0z-pQTg\" rel=\"nofollow noopener\"><img loading=\"lazy\" decoding=\"async\" src=\"https:\/\/infernews.com\/blog\/wp-content\/plugins\/wp-youtube-lyte\/lyteCache.php?origThumbUrl=https%3A%2F%2Fi.ytimg.com%2Fvi%2FLqFc0z-pQTg%2F0.jpg\" alt=\"6: Deep Learning for Natural Language &ndash; Embeddings\" width=\"853\" height=\"460\" \/><br \/>Watch this video on YouTube<\/a><\/noscript><meta itemprop=\"description\" content=\"MIT 15.773 Hands-On Deep Learning Spring 2024 Instructor: Rama Ramakrishnan View the complete course: https:\/\/ocw.mit.edu\/courses\/15-773-hands-on-deep-learning-spring-2024 YouTube Playlist: https:\/\/www.youtube.com\/playlist?list=PLUl4u3cNGP60YyhMjYmXuVmX562QcClSp Continues discussion of natural language processing with a focus on embeddings, including stand-alone and contextual embeddings. License: Creative Commons BY-NC-SAMore information at https:\/\/ocw.mit.edu\/termsMore courses at https:\/\/ocw.mit.eduSupport OCW at http:\/\/ow.ly\/a1If50zVRlQ We encourage constructive comments and discussion on OCW\u2019s YouTube and other social media channels. Personal attacks, hate speech, trolling, and inappropriate comments are not allowed and may be removed. More details at https:\/\/ocw.mit.edu\/comments.\"><\/div><\/div><div class=\"lL\" style=\"max-width:100%;width:853px;margin:5px auto;\"><\/div><figcaption><\/figcaption><\/figure>\n<figure class=\"wp-block-embed-youtube wp-block-embed is-type-video is-provider-youtube wp-embed-aspect-16-9 wp-has-aspect-ratio\"><div class=\"lyte-wrapper\" title=\"7: Deep Learning for Natural Language &ndash; Transformers\" style=\"width:853px;max-width:100%;margin:5px auto;\"><div class=\"lyMe\" id=\"WYL_IeF7aATDaw4\" itemprop=\"video\" itemscope itemtype=\"https:\/\/schema.org\/VideoObject\"><div><meta itemprop=\"thumbnailUrl\" content=\"https:\/\/infernews.com\/blog\/wp-content\/plugins\/wp-youtube-lyte\/lyteCache.php?origThumbUrl=https%3A%2F%2Fi.ytimg.com%2Fvi%2FIeF7aATDaw4%2Fhqdefault.jpg\" \/><meta itemprop=\"embedURL\" content=\"https:\/\/www.youtube.com\/embed\/IeF7aATDaw4\" \/><meta itemprop=\"duration\" content=\"PT1H16M38S\" \/><meta itemprop=\"uploadDate\" content=\"2026-01-07T15:01:34Z\" \/><\/div><meta itemprop=\"accessibilityFeature\" content=\"captions\" \/><div id=\"lyte_IeF7aATDaw4\" data-src=\"https:\/\/infernews.com\/blog\/wp-content\/plugins\/wp-youtube-lyte\/lyteCache.php?origThumbUrl=https%3A%2F%2Fi.ytimg.com%2Fvi%2FIeF7aATDaw4%2Fhqdefault.jpg\" class=\"pL\"><div class=\"tC\"><div class=\"tT\" itemprop=\"name\">7: Deep Learning for Natural Language \u2013 Transformers<\/div><\/div><div class=\"play\"><\/div><div class=\"ctrl\"><div class=\"Lctrl\"><\/div><div class=\"Rctrl\"><\/div><\/div><\/div><noscript><a href=\"https:\/\/youtu.be\/IeF7aATDaw4\" rel=\"nofollow noopener\"><img loading=\"lazy\" decoding=\"async\" src=\"https:\/\/infernews.com\/blog\/wp-content\/plugins\/wp-youtube-lyte\/lyteCache.php?origThumbUrl=https%3A%2F%2Fi.ytimg.com%2Fvi%2FIeF7aATDaw4%2F0.jpg\" alt=\"7: Deep Learning for Natural Language &ndash; Transformers\" width=\"853\" height=\"460\" \/><br \/>Watch this video on YouTube<\/a><\/noscript><meta itemprop=\"description\" content=\"MIT 15.773 Hands-On Deep Learning Spring 2024 Instructor: Rama Ramakrishnan View the complete course: https:\/\/ocw.mit.edu\/courses\/15-773-hands-on-deep-learning-spring-2024 YouTube Playlist: https:\/\/www.youtube.com\/playlist?list=PLUl4u3cNGP60YyhMjYmXuVmX562QcClSp Transformers are described via an airline travel-related example. License: Creative Commons BY-NC-SAMore information at https:\/\/ocw.mit.edu\/termsMore courses at https:\/\/ocw.mit.eduSupport OCW at http:\/\/ow.ly\/a1If50zVRlQ We encourage constructive comments and discussion on OCW\u2019s YouTube and other social media channels. Personal attacks, hate speech, trolling, and inappropriate comments are not allowed and may be removed. More details at https:\/\/ocw.mit.edu\/comments.\"><\/div><\/div><div class=\"lL\" style=\"max-width:100%;width:853px;margin:5px auto;\"><\/div><figcaption><\/figcaption><\/figure>\n<figure class=\"wp-block-embed-youtube wp-block-embed is-type-video is-provider-youtube wp-embed-aspect-16-9 wp-has-aspect-ratio\"><div class=\"lyte-wrapper\" title=\"8: Deep Learning for Natural Language &ndash; Transformers, Self-Supervised Learning\" style=\"width:853px;max-width:100%;margin:5px auto;\"><div class=\"lyMe\" id=\"WYL_v-lHsawHyaI\" itemprop=\"video\" itemscope itemtype=\"https:\/\/schema.org\/VideoObject\"><div><meta itemprop=\"thumbnailUrl\" content=\"https:\/\/infernews.com\/blog\/wp-content\/plugins\/wp-youtube-lyte\/lyteCache.php?origThumbUrl=https%3A%2F%2Fi.ytimg.com%2Fvi%2Fv-lHsawHyaI%2Fhqdefault.jpg\" \/><meta itemprop=\"embedURL\" content=\"https:\/\/www.youtube.com\/embed\/v-lHsawHyaI\" \/><meta itemprop=\"duration\" content=\"PT1H16M47S\" \/><meta itemprop=\"uploadDate\" content=\"2026-01-07T15:01:45Z\" \/><\/div><meta itemprop=\"accessibilityFeature\" content=\"captions\" \/><div id=\"lyte_v-lHsawHyaI\" data-src=\"https:\/\/infernews.com\/blog\/wp-content\/plugins\/wp-youtube-lyte\/lyteCache.php?origThumbUrl=https%3A%2F%2Fi.ytimg.com%2Fvi%2Fv-lHsawHyaI%2Fhqdefault.jpg\" class=\"pL\"><div class=\"tC\"><div class=\"tT\" itemprop=\"name\">8: Deep Learning for Natural Language \u2013 Transformers, Self-Supervised Learning<\/div><\/div><div class=\"play\"><\/div><div class=\"ctrl\"><div class=\"Lctrl\"><\/div><div class=\"Rctrl\"><\/div><\/div><\/div><noscript><a href=\"https:\/\/youtu.be\/v-lHsawHyaI\" rel=\"nofollow noopener\"><img loading=\"lazy\" decoding=\"async\" src=\"https:\/\/infernews.com\/blog\/wp-content\/plugins\/wp-youtube-lyte\/lyteCache.php?origThumbUrl=https%3A%2F%2Fi.ytimg.com%2Fvi%2Fv-lHsawHyaI%2F0.jpg\" alt=\"8: Deep Learning for Natural Language &ndash; Transformers, Self-Supervised Learning\" width=\"853\" height=\"460\" \/><br \/>Watch this video on YouTube<\/a><\/noscript><meta itemprop=\"description\" content=\"MIT 15.773 Hands-On Deep Learning Spring 2024 Instructor: Rama Ramakrishnan View the complete course: https:\/\/ocw.mit.edu\/courses\/15-773-hands-on-deep-learning-spring-2024 YouTube Playlist: https:\/\/www.youtube.com\/playlist?list=PLUl4u3cNGP60YyhMjYmXuVmX562QcClSp A deeper dive into transformers and how to use them. License: Creative Commons BY-NC-SAMore information at https:\/\/ocw.mit.edu\/termsMore courses at https:\/\/ocw.mit.eduSupport OCW at http:\/\/ow.ly\/a1If50zVRlQ We encourage constructive comments and discussion on OCW\u2019s YouTube and other social media channels. Personal attacks, hate speech, trolling, and inappropriate comments are not allowed and may be removed. More details at https:\/\/ocw.mit.edu\/comments.\"><\/div><\/div><div class=\"lL\" style=\"max-width:100%;width:853px;margin:5px auto;\"><\/div><figcaption><\/figcaption><\/figure>\n<figure class=\"wp-block-embed-youtube wp-block-embed is-type-video is-provider-youtube wp-embed-aspect-16-9 wp-has-aspect-ratio\"><div class=\"lyte-wrapper\" title=\"9: Generative AI &ndash; Large Language Models (LLMs) and Retrieval Augmented Generation (RAG)\" style=\"width:853px;max-width:100%;margin:5px auto;\"><div class=\"lyMe\" id=\"WYL_KGDe1QvfKJ8\" itemprop=\"video\" itemscope itemtype=\"https:\/\/schema.org\/VideoObject\"><div><meta itemprop=\"thumbnailUrl\" content=\"https:\/\/infernews.com\/blog\/wp-content\/plugins\/wp-youtube-lyte\/lyteCache.php?origThumbUrl=https%3A%2F%2Fi.ytimg.com%2Fvi%2FKGDe1QvfKJ8%2Fhqdefault.jpg\" \/><meta itemprop=\"embedURL\" content=\"https:\/\/www.youtube.com\/embed\/KGDe1QvfKJ8\" \/><meta itemprop=\"duration\" content=\"PT1H14M30S\" \/><meta itemprop=\"uploadDate\" content=\"2026-01-07T15:01:44Z\" \/><\/div><meta itemprop=\"accessibilityFeature\" content=\"captions\" \/><div id=\"lyte_KGDe1QvfKJ8\" data-src=\"https:\/\/infernews.com\/blog\/wp-content\/plugins\/wp-youtube-lyte\/lyteCache.php?origThumbUrl=https%3A%2F%2Fi.ytimg.com%2Fvi%2FKGDe1QvfKJ8%2Fhqdefault.jpg\" class=\"pL\"><div class=\"tC\"><div class=\"tT\" itemprop=\"name\">9: Generative AI \u2013 Large Language Models (LLMs) and Retrieval Augmented Generation (RAG)<\/div><\/div><div class=\"play\"><\/div><div class=\"ctrl\"><div class=\"Lctrl\"><\/div><div class=\"Rctrl\"><\/div><\/div><\/div><noscript><a href=\"https:\/\/youtu.be\/KGDe1QvfKJ8\" rel=\"nofollow noopener\"><img loading=\"lazy\" decoding=\"async\" src=\"https:\/\/infernews.com\/blog\/wp-content\/plugins\/wp-youtube-lyte\/lyteCache.php?origThumbUrl=https%3A%2F%2Fi.ytimg.com%2Fvi%2FKGDe1QvfKJ8%2F0.jpg\" alt=\"9: Generative AI &ndash; Large Language Models (LLMs) and Retrieval Augmented Generation (RAG)\" width=\"853\" height=\"460\" \/><br \/>Watch this video on YouTube<\/a><\/noscript><meta itemprop=\"description\" content=\"MIT 15.773 Hands-On Deep Learning Spring 2024 Instructor: Rama Ramakrishnan View the complete course: https:\/\/ocw.mit.edu\/courses\/15-773-hands-on-deep-learning-spring-2024 YouTube Playlist: https:\/\/www.youtube.com\/playlist?list=PLUl4u3cNGP60YyhMjYmXuVmX562QcClSp Introduces next word prediction using the transformer encoder architecture from the previous class. License: Creative Commons BY-NC-SAMore information at https:\/\/ocw.mit.edu\/termsMore courses at https:\/\/ocw.mit.eduSupport OCW at http:\/\/ow.ly\/a1If50zVRlQ We encourage constructive comments and discussion on OCW\u2019s YouTube and other social media channels. Personal attacks, hate speech, trolling, and inappropriate comments are not allowed and may be removed. More details at https:\/\/ocw.mit.edu\/comments.\"><\/div><\/div><div class=\"lL\" style=\"max-width:100%;width:853px;margin:5px auto;\"><\/div><figcaption><\/figcaption><\/figure>\n<figure class=\"wp-block-embed-youtube wp-block-embed is-type-video is-provider-youtube wp-embed-aspect-16-9 wp-has-aspect-ratio\"><div class=\"lyte-wrapper\" title=\"10: Generative AI &ndash; Adapting LLMs with Parameter-Efficient Fine-Tuning\" style=\"width:853px;max-width:100%;margin:5px auto;\"><div class=\"lyMe\" id=\"WYL_d-tngNnaG4U\" itemprop=\"video\" itemscope itemtype=\"https:\/\/schema.org\/VideoObject\"><div><meta itemprop=\"thumbnailUrl\" content=\"https:\/\/infernews.com\/blog\/wp-content\/plugins\/wp-youtube-lyte\/lyteCache.php?origThumbUrl=https%3A%2F%2Fi.ytimg.com%2Fvi%2Fd-tngNnaG4U%2Fhqdefault.jpg\" \/><meta itemprop=\"embedURL\" content=\"https:\/\/www.youtube.com\/embed\/d-tngNnaG4U\" \/><meta itemprop=\"duration\" content=\"PT1H17M43S\" \/><meta itemprop=\"uploadDate\" content=\"2026-01-07T15:01:47Z\" \/><\/div><meta itemprop=\"accessibilityFeature\" content=\"captions\" \/><div id=\"lyte_d-tngNnaG4U\" data-src=\"https:\/\/infernews.com\/blog\/wp-content\/plugins\/wp-youtube-lyte\/lyteCache.php?origThumbUrl=https%3A%2F%2Fi.ytimg.com%2Fvi%2Fd-tngNnaG4U%2Fhqdefault.jpg\" class=\"pL\"><div class=\"tC\"><div class=\"tT\" itemprop=\"name\">10: Generative AI \u2013 Adapting LLMs with Parameter-Efficient Fine-Tuning<\/div><\/div><div class=\"play\"><\/div><div class=\"ctrl\"><div class=\"Lctrl\"><\/div><div class=\"Rctrl\"><\/div><\/div><\/div><noscript><a href=\"https:\/\/youtu.be\/d-tngNnaG4U\" rel=\"nofollow noopener\"><img loading=\"lazy\" decoding=\"async\" src=\"https:\/\/infernews.com\/blog\/wp-content\/plugins\/wp-youtube-lyte\/lyteCache.php?origThumbUrl=https%3A%2F%2Fi.ytimg.com%2Fvi%2Fd-tngNnaG4U%2F0.jpg\" alt=\"10: Generative AI &ndash; Adapting LLMs with Parameter-Efficient Fine-Tuning\" width=\"853\" height=\"460\" \/><br \/>Watch this video on YouTube<\/a><\/noscript><meta itemprop=\"description\" content=\"MIT 15.773 Hands-On Deep Learning Spring 2024 Instructor: Rama Ramakrishnan View the complete course: https:\/\/ocw.mit.edu\/courses\/15-773-hands-on-deep-learning-spring-2024 YouTube Playlist: https:\/\/www.youtube.com\/playlist?list=PLUl4u3cNGP60YyhMjYmXuVmX562QcClSp Addresses Generative Pretrained Transformers (GPTs) version differences and nuances of training data, instruction tuning, and adapting base language learning models (LLMs). License: Creative Commons BY-NC-SAMore information at https:\/\/ocw.mit.edu\/termsMore courses at https:\/\/ocw.mit.eduSupport OCW at http:\/\/ow.ly\/a1If50zVRlQ We encourage constructive comments and discussion on OCW\u2019s YouTube and other social media channels. Personal attacks, hate speech, trolling, and inappropriate comments are not allowed and may be removed. More details at https:\/\/ocw.mit.edu\/comments.\"><\/div><\/div><div class=\"lL\" style=\"max-width:100%;width:853px;margin:5px auto;\"><\/div><figcaption><\/figcaption><\/figure>\n","protected":false},"excerpt":{"rendered":"","protected":false},"author":1,"featured_media":0,"parent":0,"menu_order":0,"comment_status":"closed","ping_status":"closed","template":"","meta":{"ai_generated_summary":"","footnotes":""},"class_list":["post-8866","page","type-page","status-publish","hentry"],"_links":{"self":[{"href":"https:\/\/infernews.com\/blog\/wp-json\/wp\/v2\/pages\/8866","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/infernews.com\/blog\/wp-json\/wp\/v2\/pages"}],"about":[{"href":"https:\/\/infernews.com\/blog\/wp-json\/wp\/v2\/types\/page"}],"author":[{"embeddable":true,"href":"https:\/\/infernews.com\/blog\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/infernews.com\/blog\/wp-json\/wp\/v2\/comments?post=8866"}],"version-history":[{"count":8,"href":"https:\/\/infernews.com\/blog\/wp-json\/wp\/v2\/pages\/8866\/revisions"}],"predecessor-version":[{"id":8876,"href":"https:\/\/infernews.com\/blog\/wp-json\/wp\/v2\/pages\/8866\/revisions\/8876"}],"wp:attachment":[{"href":"https:\/\/infernews.com\/blog\/wp-json\/wp\/v2\/media?parent=8866"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}