{"id":1890,"date":"2022-05-25T22:34:47","date_gmt":"2022-05-25T22:34:47","guid":{"rendered":"https:\/\/eccb2022.org\/?page_id=1890"},"modified":"2022-07-01T07:28:18","modified_gmt":"2022-07-01T07:28:18","slug":"ntb-t03","status":"publish","type":"page","link":"https:\/\/eccb2022.org\/ntb-t03\/","title":{"rendered":"NTB-T03"},"content":{"rendered":"\n<div class=\"wp-block-stackable-heading stk-block-heading stk-block stk-6f6b038\" data-block-id=\"6f6b038\"><style>.stk-6f6b038 .stk-block-heading__bottom-line{height:1px !important;background-color:var(u002du002dpaletteColor2,#f7b032) !important;margin-top:12px !important}<\/style><h5 class=\"stk-block-heading__text\"><span style=\"color: var(--paletteColor4, #0081a7);\" class=\"stk-highlight\"><strong>Title<\/strong><\/span><\/h5><div class=\"stk-block-heading__bottom-line\"><\/div><\/div>\n\n\n\n<div class=\"wp-block-stackable-heading stk-block-heading stk-block stk-9ed2aad\" data-block-id=\"9ed2aad\"><h3 class=\"stk-block-heading__text\">Deep Learning For Biological Sequence Data: From Convolutional Neural Networks To Transformers<\/h3><\/div>\n\n\n\n<div class=\"wp-block-stackable-heading stk-block-heading stk-block stk-77074a6\" data-block-id=\"77074a6\"><style>.stk-77074a6 .stk-block-heading__bottom-line{height:1px !important;background-color:var(u002du002dpaletteColor2,#f7b032) !important;margin-top:12px !important}<\/style><h5 class=\"stk-block-heading__text\"><span style=\"color: var(--paletteColor4, #0081a7);\" class=\"stk-highlight\"><strong><span style=\"color: var(--paletteColor4, #0081a7);\" class=\"stk-highlight\"><span style=\"color: var(--paletteColor4, #1a928e);\" class=\"stk-highlight\"><span style=\"color: var(--paletteColor4, #0081a7);\" class=\"stk-highlight\"><span style=\"color: var(--paletteColor4, #0081a7);\" class=\"stk-highlight\"><strong><span style=\"color: var(--paletteColor4, #0081a7);\" class=\"stk-highlight\"><span style=\"color: var(--paletteColor4, #1a928e);\" class=\"stk-highlight\"><span style=\"color: var(--paletteColor4, #0081a7);\" class=\"stk-highlight\">Tutorial<\/span><\/span><\/span><\/strong><\/span> details<\/span><\/span><\/span><\/strong><\/span><\/h5><div class=\"stk-block-heading__bottom-line\"><\/div><\/div>\n\n\n\n<ul><li>Date: Sunday, September 18th<\/li><li>Time: 09:00 to 13:00 CEST (Slot 21)<\/li><li>Format: Face-to-face<\/li><li>Room: TBD<\/li><\/ul>\n\n\n\n<div class=\"wp-block-stackable-heading stk-block-heading stk-block stk-0994530\" data-block-id=\"0994530\"><style>.stk-0994530 .stk-block-heading__bottom-line{height:1px !important;background-color:var(u002du002dpaletteColor2,#f7b032) !important;margin-top:12px !important}<\/style><h5 class=\"stk-block-heading__text\">Instructors<\/h5><div class=\"stk-block-heading__bottom-line\"><\/div><\/div>\n\n\n\n<ul><li><strong>Panagiotis Alexiou<\/strong>, PhD. Central European Institute of Technology, Masaryk University (Czech Republic) <\/li><li><strong>Petr Simecek<\/strong>, PhD. Central European Institute of Technology, Masaryk University (Czech Republic)<\/li><li><strong>David Cechak<\/strong>, PhD student. Central European Institute of Technology, Masaryk University (Czech Republic)<\/li><li><strong>Vlastimil Martinek<\/strong>, PhD student. Central European Institute of Technology, Masaryk University (Czech Republic)<\/li><\/ul>\n\n\n\n<div class=\"wp-block-stackable-heading stk-block-heading stk-block stk-dafbd15\" data-block-id=\"dafbd15\"><style>.stk-dafbd15 .stk-block-heading__bottom-line{height:1px !important;background-color:var(u002du002dpaletteColor2,#f7b032) !important;margin-top:12px !important}<\/style><h5 class=\"stk-block-heading__text\">Summary<\/h5><div class=\"stk-block-heading__bottom-line\"><\/div><\/div>\n\n\n\n<p>Computational Biologists have been using Machine Learning techniques based on Artificial Neural Networks for decades. New developments in the Machine Learning field over the past years have revolutionized the efficiency of Neural Networks and brought us to the era of Deep Learning. In the news, you can read about Deep Learning beating experts in Go, Chess and StarCraft, translating texts and speech between languages, turning the steering wheels of self-driving cars and even tagging kittens, Not-Hotdogs in images. In our field, we have witnessed such systems reaching competitive accuracy with experienced radiologists, predicting the folding of proteins and calling single nucleotide polymorphisms in genomic data better than any other method.<br>In this tutorial we utilize four powerful components that are freely available for use:<br>TensorFlow is an open-source library for deep learning and machine learning in general. Thanks to the second one, Google Collaboratory, computational resources needed to train<br>TensorFlow models are available without cost. The third, TensorFlow.js, will enable us to deploy the trained model as a static web page that can be easily hosted, e.g. on GitHub Pages. And finally, Hugging Face libraries, datasets, and models will enable us to run complex transformer models with four lines of code.<br>The key part of the tutorial will be the evaluation and interpretation of the trained model. What could go wrong and how to diagnose it? We will start with simple techniques, like measuring the impact of simple perturbation, and end with an Integrated Gradient method to identify parts of the input that mostly contributed to the decision.<\/p>\n\n\n\n<div class=\"wp-block-stackable-heading stk-block-heading stk-block stk-4a8e43e\" data-block-id=\"4a8e43e\"><style>.stk-4a8e43e .stk-block-heading__bottom-line{height:1px !important;background-color:var(u002du002dpaletteColor2,#f7b032) !important;margin-top:12px !important}<\/style><h5 class=\"stk-block-heading__text\"><strong>Intended audience<\/strong><\/h5><div class=\"stk-block-heading__bottom-line\"><\/div><\/div>\n\n\n\n<p>This tutorial is intended for students and practitioners interested in getting their hands dirty with neural networks. It is designed to be an introduction and a starting point for further work and study. Beginners are welcome. Familiarity with Python is necessary, and experience with Jupyter Notebooks, pandas &amp; NumPy will be useful.<\/p>\n\n\n\n<div class=\"wp-block-stackable-heading oculto stk-block-heading stk-block stk-4cdfd01\" data-block-id=\"4cdfd01\"><style>.stk-4cdfd01 .stk-block-heading__bottom-line{height:1px !important;background-color:var(u002du002dpaletteColor2,#f7b032) !important;margin-top:12px !important}<\/style><h5 class=\"stk-block-heading__text\"><strong>Prerequisites<\/strong><\/h5><div class=\"stk-block-heading__bottom-line\"><\/div><\/div>\n\n\n\n<ul><li><\/li><\/ul>\n\n\n\n<div class=\"wp-block-stackable-heading stk-block-heading stk-block stk-cdd954b\" data-block-id=\"cdd954b\"><style>.stk-cdd954b .stk-block-heading__bottom-line{height:1px !important;background-color:var(u002du002dpaletteColor2,#f7b032) !important;margin-top:12px !important}<\/style><h5 class=\"stk-block-heading__text\"><strong>Maximum number of attendees<\/strong><\/h5><div class=\"stk-block-heading__bottom-line\"><\/div><\/div>\n\n\n\n<p>35<\/p>\n\n\n\n<div class=\"wp-block-stackable-heading stk-block-heading stk-block stk-1689a19\" data-block-id=\"1689a19\"><style>.stk-1689a19 .stk-block-heading__bottom-line{height:1px !important;background-color:var(u002du002dpaletteColor2,#f7b032) !important;margin-top:12px !important}<\/style><h5 class=\"stk-block-heading__text\"><strong><strong>Material required (for participants)<\/strong><\/strong><\/h5><div class=\"stk-block-heading__bottom-line\"><\/div><\/div>\n\n\n\n<p>Participants should bring their own laptops and a web browser (not IE 6.0). They will need to have a Google account (e.g. Gmail) to access Collaboratory.<\/p>\n\n\n\n<div class=\"wp-block-stackable-heading stk-block-heading stk-block stk-38c235b\" data-block-id=\"38c235b\"><style>.stk-38c235b .stk-block-heading__bottom-line{height:1px !important;background-color:var(u002du002dpaletteColor2,#f7b032) !important;margin-top:12px !important}<\/style><h5 class=\"stk-block-heading__text\"><strong>Provisional schedule<\/strong><\/h5><div class=\"stk-block-heading__bottom-line\"><\/div><\/div>\n\n\n\n<div class=\"wp-block-stackable-columns oculto stk-block-columns stk-block stk-8dda295\" data-block-id=\"8dda295\"><div class=\"stk-row stk-inner-blocks stk-block-content stk-content-align stk-8dda295-column\">\n<div class=\"wp-block-stackable-column stk-block-column stk-column stk-block stk-c3796a7\" data-block-id=\"c3796a7\"><div class=\"stk-column-wrapper stk-block-column__content stk-container stk-c3796a7-container stk--no-background stk--no-padding\"><div class=\"stk-block-content stk-inner-blocks\">\n<ul><li>09:00 \u2013 10:00 Part I: Introduction<\/li><\/ul>\n\n\n\n<p>Intro to deep learning: What are neural networks and why have they become so popular?<br>MNIST dataset: Fully connected vs. convolutional neural networks<br>Classification of biomedical images: ImageNet, ResNet, transfer learning<br>CNN applied to sequential (genomic) data<\/p>\n\n\n\n<ul><li>10:00 \u2013 10:30 Part II: Recurrent Neural Networks<\/li><\/ul>\n\n\n\n<ul><li>10:30 \u2013 11:00 Break<\/li><\/ul>\n\n\n\n<ul><li>11:00 \u2013 12:00 Part III: Deployment and interpretation<\/li><\/ul>\n\n\n\n<p>Save &amp; convert: how to save TF model and how to convert it to TFjs<br>Interpretation: simple techniques like measuring the impact of a random change on a position or interpretation of the first layer convolutions<br>Integrated Gradients: explanation and examples of use<\/p>\n\n\n\n<ul><li>12:00 \u2013 12:30 Part IV: Transformers<\/li><\/ul>\n\n\n\n<p>What is a transformer? Intro to the architecture, differences from CNN and RNN, and the HuggingFace transformers library<br>How to use pre-trained models? Example on pre-trained proteins transformers using HuggingFace<\/p>\n<\/div><\/div><\/div>\n<\/div><\/div>\n\n\n\n<figure class=\"wp-block-table tabla-ntb is-style-regular\" style=\"font-size:15px\"><table><thead><tr><th class=\"has-text-align-left\" data-align=\"left\"> <strong>T<\/strong>IME <\/th><th class=\"has-text-align-left\" data-align=\"left\"><strong>CONTENT<\/strong><\/th><\/tr><\/thead><tbody><tr><td class=\"has-text-align-left\" data-align=\"left\"><span style=\"color: var(--paletteColor4, #0081a7);\" class=\"stk-highlight\"><strong>09:00 \u2013 10:00<\/strong><\/span><\/td><td class=\"has-text-align-left\" data-align=\"left\"><strong>Part I: Introduction<\/strong><br>Intro to deep learning: What are neural networks and why have they become so popular?<br>MNIST dataset: Fully connected vs. convolutional neural networks<br>Classification of biomedical images: ImageNet, ResNet, transfer learning<br>CNN applied to sequential (genomic) data<\/td><\/tr><tr><td class=\"has-text-align-left\" data-align=\"left\"><span style=\"color: var(--paletteColor4, #0081a7);\" class=\"stk-highlight\"><strong>10:00 \u2013 10:30<\/strong><\/span><\/td><td class=\"has-text-align-left\" data-align=\"left\"><strong>Part II: Recurrent Neural Networks<\/strong><\/td><\/tr><tr><td class=\"has-text-align-left\" data-align=\"left\"><strong><span style=\"color: var(--paletteColor4, #0081a7);\" class=\"stk-highlight\">10:30 \u2013 11:00<\/span><\/strong><\/td><td class=\"has-text-align-left\" data-align=\"left\"><strong>Break<\/strong><\/td><\/tr><tr><td class=\"has-text-align-left\" data-align=\"left\"><strong><span style=\"color: var(--paletteColor4, #0081a7);\" class=\"stk-highlight\">11:00 \u2013 12:00<\/span><\/strong><\/td><td class=\"has-text-align-left\" data-align=\"left\"><strong>Part III: Deployment and interpretation<\/strong><br>Save &amp; convert: how to save TF model and how to convert it to TFjs<br>Interpretation: simple techniques like measuring the impact of a random change on a position or interpretation of the first layer convolutions<br>Integrated Gradients: explanation and examples of use<\/td><\/tr><tr><td class=\"has-text-align-left\" data-align=\"left\"><strong><span style=\"color: var(--paletteColor4, #0081a7);\" class=\"stk-highlight\">12:00 \u2013 12:30<\/span><\/strong> <\/td><td class=\"has-text-align-left\" data-align=\"left\"><strong>Part IV: Transformers<\/strong><br>What is a transformer? Intro to the architecture, differences from CNN and RNN, and the HuggingFace transformers library<br>How to use pre-trained models? Example on pre-trained proteins transformers using HuggingFace<\/td><\/tr><\/tbody><\/table><\/figure>\n","protected":false},"excerpt":{"rendered":"<p>Title Deep Learning For Biological Sequence Data: From Convolutional Neural Networks To Transformers Tutorial details Date: Sunday, September 18th Time: 09:00 to 13:00 CEST (Slot 21) Format: Face-to-face Room: TBD Instructors Panagiotis Alexiou, PhD. Central European Institute of Technology, Masaryk University (Czech Republic) Petr Simecek, PhD. Central European Institute of Technology, Masaryk University (Czech Republic) David Cechak, PhD student. Central European Institute of Technology, Masaryk University (Czech Republic) Vlastimil Martinek, PhD student. Central European Institute of Technology, Masaryk University (Czech Republic) Summary Computational Biologists have been using Machine Learning techniques based on Artificial Neural Networks for decades. New developments in\u2026<\/p>\n","protected":false},"author":2,"featured_media":0,"parent":0,"menu_order":0,"comment_status":"closed","ping_status":"closed","template":"","meta":[],"blocksy_meta":{"styles_descriptor":{"styles":{"desktop":"","tablet":"","mobile":""},"google_fonts":[],"version":4},"page_title_panel":"","has_hero_section":"default","7b9ded946d4680066060ddae606a4869":"","hero_section":"type-1","hero_elements":[{"id":"custom_title","enabled":true,"heading_tag":"h1","title":"Inicio"},{"id":"custom_description","enabled":true,"description_visibility":{"desktop":true,"tablet":true,"mobile":false}},{"id":"custom_meta","enabled":false,"meta_elements":[{"id":"author","enabled":true,"label":"Por","has_author_avatar":"yes","avatar_size":25},{"id":"post_date","enabled":true,"label":"El","date_format_source":"default","date_format":"M j, Y"},{"id":"updated_date","enabled":false,"label":"El","date_format_source":"default","date_format":"M j, Y"},{"id":"categories","enabled":false,"label":"Dentro","style":"simple"},{"id":"comments","enabled":true}],"page_meta_elements":{"joined":true,"articles_count":true,"comments":true}},{"id":"breadcrumbs","enabled":false}],"7e7ee7f45a5eac24c3975bb449faee22":"","hero_alignment1":"CT_CSS_SKIP_RULE","hero_margin":40,"hero_alignment2":"center","hero_vertical_alignment":"center","d1ec673d633ad68747a95aca445fd9cb":"","hero_structure":"narrow","9134ae46ae942dc09e310cecafbb9abc":"","page_title_bg_type":"featured_image","custom_hero_background":{"attachment_id":null},"parallax":{"desktop":false,"tablet":false,"mobile":false},"af2025ba232bd9346392fb881545369c":"","hero_height":"250px","pageTitleFont":{"family":"Default","variation":"Default","size":"30px","line-height":"CT_CSS_SKIP_RULE","letter-spacing":"CT_CSS_SKIP_RULE","text-transform":"CT_CSS_SKIP_RULE","text-decoration":"CT_CSS_SKIP_RULE"},"pageTitleFontColor":{"default":{"color":"CT_CSS_SKIP_RULEDEFAULT"}},"pageMetaFont":{"family":"Default","variation":"n6","size":"12px","line-height":"1.3","letter-spacing":"CT_CSS_SKIP_RULE","text-transform":"uppercase","text-decoration":"CT_CSS_SKIP_RULE"},"pageMetaFontColor":{"default":{"color":"CT_CSS_SKIP_RULEDEFAULT"},"hover":{"color":"CT_CSS_SKIP_RULEDEFAULT"}},"page_meta_button_type_font_colors":{"default":{"color":"CT_CSS_SKIP_RULEDEFAULT"},"hover":{"color":"CT_CSS_SKIP_RULEDEFAULT"}},"page_meta_button_type_background_colors":{"default":{"color":"CT_CSS_SKIP_RULEDEFAULT"},"hover":{"color":"CT_CSS_SKIP_RULEDEFAULT"}},"pageExcerptFont":{"family":"Default","variation":"Default","size":"CT_CSS_SKIP_RULE","line-height":"CT_CSS_SKIP_RULE","letter-spacing":"CT_CSS_SKIP_RULE","text-transform":"CT_CSS_SKIP_RULE","text-decoration":"CT_CSS_SKIP_RULE"},"pageExcerptColor":{"default":{"color":"CT_CSS_SKIP_RULEDEFAULT"}},"breadcrumbsFont":{"family":"Default","variation":"Default","size":"CT_CSS_SKIP_RULE","line-height":"CT_CSS_SKIP_RULE","letter-spacing":"CT_CSS_SKIP_RULE","text-transform":"CT_CSS_SKIP_RULE","text-decoration":"CT_CSS_SKIP_RULE"},"breadcrumbsFontColor":{"default":{"color":"CT_CSS_SKIP_RULEDEFAULT"},"initial":{"color":"CT_CSS_SKIP_RULEDEFAULT"},"hover":{"color":"CT_CSS_SKIP_RULEDEFAULT"}},"pageTitleOverlay":{"background_type":"color","background_pattern":"type-1","background_image":{"attachment_id":null,"x":0,"y":0},"gradient":"linear-gradient(135deg,rgba(6,147,227,1) 0%,rgb(155,81,224) 100%)","background_repeat":"repeat","background_size":"auto","background_attachment":"scroll","patternColor":{"default":{"color":"#e5e7ea"}},"overlayColor":{"default":{"color":"CT_CSS_SKIP_RULE"}},"backgroundColor":{"default":{"color":"CT_CSS_SKIP_RULE"}}},"pageTitleBackground":{"background_type":"color","background_pattern":"type-1","background_image":{"attachment_id":null,"x":0,"y":0},"gradient":"linear-gradient(135deg,rgba(6,147,227,1) 0%,rgb(155,81,224) 100%)","background_repeat":"repeat","background_size":"auto","background_attachment":"scroll","patternColor":{"default":{"color":"#e5e7ea"}},"overlayColor":{"default":{"color":"CT_CSS_SKIP_RULE"}},"backgroundColor":{"default":{"color":"var(--paletteColor6)"}}},"pageTitlePadding":{"top":"50px","bottom":"50px","left":"auto","right":"auto","linked":true},"ff59f1ce76d65ee65bad3f06718272f6":"","page_structure_type":"type-3","9015a680e092b06588ef574280471413":"","content_style_source":"inherit","content_style":"wide","vertical_spacing_source":"inherit","content_area_spacing":"both","background":{"background_type":"color","background_pattern":"type-1","background_image":{"attachment_id":null,"x":0,"y":0},"gradient":"linear-gradient(135deg,rgba(6,147,227,1) 0%,rgb(155,81,224) 100%)","background_repeat":"repeat","background_size":"auto","background_attachment":"scroll","patternColor":{"default":{"color":"#e5e7ea"}},"overlayColor":{"default":{"color":"CT_CSS_SKIP_RULE"}},"backgroundColor":{"default":{"color":"CT_CSS_SKIP_RULE"}}},"content_background":{"background_type":"color","background_pattern":"type-1","background_image":{"attachment_id":null,"x":0,"y":0},"gradient":"linear-gradient(135deg,rgba(6,147,227,1) 0%,rgb(155,81,224) 100%)","background_repeat":"repeat","background_size":"auto","background_attachment":"scroll","patternColor":{"default":{"color":"#e5e7ea"}},"overlayColor":{"default":{"color":"CT_CSS_SKIP_RULE"}},"backgroundColor":{"default":{"color":"var(--paletteColor8)"}}},"content_boxed_shadow":{"inherit":false,"blur":18,"spread":-6,"v_offset":12,"h_offset":0,"inset":false,"enable":true,"color":{"color":"rgba(34, 56, 101, 0.04)"}},"boxed_content_spacing":{"desktop":{"top":"40px","bottom":"40px","left":"40px","right":"40px","linked":true},"tablet":{"top":"35px","bottom":"35px","left":"35px","right":"35px","linked":true},"mobile":{"top":"20px","bottom":"20px","left":"20px","right":"20px","linked":true}},"content_boxed_radius":{"top":"3px","bottom":"3px","left":"3px","right":"3px","linked":true},"c17a8304e5e66c0922c2d4f80257a4e2":"","disable_featured_image":"no","disable_share_box":"no","disable_header":"no","disable_footer":"no"},"featured_image_urls":{"full":"","thumbnail":"","medium":"","medium_large":"","large":"","1536x1536":"","2048x2048":""},"post_excerpt_stackable":"<p>Title Deep Learning For Biological Sequence Data: From Convolutional Neural Networks To Transformers Tutorial details Date: Sunday, September 18thTime: 09:00 to 13:00 CEST (Slot 21)Format: Face-to-faceRoom: TBD Instructors Panagiotis Alexiou, PhD. Central European Institute of Technology, Masaryk University (Czech Republic) Petr Simecek, PhD. Central European Institute of Technology, Masaryk University (Czech Republic)David Cechak, PhD student. Central European Institute of Technology, Masaryk University (Czech Republic)Vlastimil Martinek, PhD student. Central European Institute of Technology, Masaryk University (Czech Republic) Summary Computational Biologists have been using Machine Learning techniques based on Artificial Neural Networks for decades. New developments in the Machine Learning field over&hellip;<\/p>\n","category_list":"","author_info":{"name":"victorcuencaharo","url":"https:\/\/eccb2022.org\/author\/victorcuencaharo\/"},"comments_num":"0 comments","_links":{"self":[{"href":"https:\/\/eccb2022.org\/wp-json\/wp\/v2\/pages\/1890"}],"collection":[{"href":"https:\/\/eccb2022.org\/wp-json\/wp\/v2\/pages"}],"about":[{"href":"https:\/\/eccb2022.org\/wp-json\/wp\/v2\/types\/page"}],"author":[{"embeddable":true,"href":"https:\/\/eccb2022.org\/wp-json\/wp\/v2\/users\/2"}],"replies":[{"embeddable":true,"href":"https:\/\/eccb2022.org\/wp-json\/wp\/v2\/comments?post=1890"}],"version-history":[{"count":19,"href":"https:\/\/eccb2022.org\/wp-json\/wp\/v2\/pages\/1890\/revisions"}],"predecessor-version":[{"id":2652,"href":"https:\/\/eccb2022.org\/wp-json\/wp\/v2\/pages\/1890\/revisions\/2652"}],"wp:attachment":[{"href":"https:\/\/eccb2022.org\/wp-json\/wp\/v2\/media?parent=1890"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}