[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"detail-sidebar-cat-0-en-105":3,"doc-seo-290421-105":59,"doc-detail-290421-en":130},{"code":4,"msg":5,"data":6},0,"success",[7,13,18,23,28,33,38,43,48,51,55],{"id":8,"doc_module":4,"doc_module_name":9,"category_name":10,"show_sort_weight":11,"slug":12},1,"Document","Story & Novel",90,"story-novel",{"id":14,"doc_module":4,"doc_module_name":9,"category_name":15,"show_sort_weight":16,"slug":17},2,"Literature",80,"literature",{"id":19,"doc_module":4,"doc_module_name":9,"category_name":20,"show_sort_weight":21,"slug":22},4,"Exam",70,"exam",{"id":24,"doc_module":4,"doc_module_name":9,"category_name":25,"show_sort_weight":26,"slug":27},5,"Comic",60,"comic",{"id":29,"doc_module":4,"doc_module_name":9,"category_name":30,"show_sort_weight":31,"slug":32},6,"Technology",50,"technology",{"id":34,"doc_module":4,"doc_module_name":9,"category_name":35,"show_sort_weight":36,"slug":37},7,"Healthcare",40,"healthcare",{"id":39,"doc_module":4,"doc_module_name":9,"category_name":40,"show_sort_weight":41,"slug":42},8,"Research & Report",30,"research-report",{"id":44,"doc_module":4,"doc_module_name":9,"category_name":45,"show_sort_weight":46,"slug":47},9,"Religion & Spirituality",20,"religion-spirituality",{"id":46,"doc_module":4,"doc_module_name":9,"category_name":49,"show_sort_weight":46,"slug":50},"World Cup","world-cup",{"id":52,"doc_module":4,"doc_module_name":9,"category_name":53,"show_sort_weight":52,"slug":54},10,"Lifestyle","lifestyle",{"id":56,"doc_module":4,"doc_module_name":9,"category_name":57,"show_sort_weight":24,"slug":58},19,"General","general",{"code":4,"msg":60,"data":61},"ok",{"site_id":62,"language":63,"slug":64,"title":65,"keywords":66,"description":67,"schema_data":68,"social_meta":123,"head_meta":125,"extra_data":127,"updated_unix":129},105,"en","modern-machine-learning-for-lhc-physicists","Modern Machine Learning for LHC Physicists","","Modern machine learning is reshaping particle physics workflows, and the lecture notes address how young researchers can keep pace. The material introduces neural networks with an LHC-specific motivation, then surveys key methods for LHC physics tasks, including classification, unsupervised classification, generative networks, and inverse problems. Two central themes guide the discussion: well-defined loss functions tailored to each task and uncertainty-aware networks. Applications also include elements of theoretical LHC physics, with examples drawn from recent particle-physics literature and frequent updates.",{"@graph":69,"@context":122},[70,84,105],{"@type":71,"itemListElement":72},"BreadcrumbList",[73,77,79,82],{"item":74,"name":75,"@type":76,"position":8},"https://docshare.wps.com","Home","ListItem",{"item":78,"name":9,"@type":76,"position":14},"https://docshare.wps.com/document/",{"item":80,"name":40,"@type":76,"position":81},"https://docshare.wps.com/document/research-report/",3,{"item":83,"name":65,"@type":76,"position":19},"https://docshare.wps.com/document/modern-machine-learning-for-lhc-physicists/290421/",{"url":83,"name":65,"@type":85,"image":86,"author":91,"headline":65,"publisher":94,"fileFormat":97,"inLanguage":63,"description":67,"dateModified":98,"datePublished":99,"encodingFormat":97,"isAccessibleForFree":100,"interactionStatistic":101},"DigitalDocument",{"url":87,"@type":88,"width":89,"height":90},"https://docshare.wps.com/thumbnails/modern-machine-learning-for-lhc-physicists/290421.png","ImageObject",300,407,{"name":92,"@type":93},"Eliana","Person",{"url":74,"name":95,"@type":96},"DocShare","Organization","application/pdf","2026-11-06","2026-09-17",true,{"@type":102,"interactionType":103,"userInteractionCount":52},"InteractionCounter",{"@type":104},"ViewAction",{"@type":106,"mainEntity":107},"FAQPage",[108,114,118],{"name":109,"@type":110,"acceptedAnswer":111},"What is the purpose of these lecture notes for LHC researchers?","Question",{"text":112,"@type":113},"They aim to help students apply modern machine-learning methods to a broad range of LHC physics problems as quickly as possible, starting from basic particle-physics knowledge.","Answer",{"name":115,"@type":110,"acceptedAnswer":116},"Which topics from machine learning are covered?",{"text":117,"@type":113},"The notes cover neural-network basics, classification, unsupervised classification, generative networks, and inverse problems, including simulation-based approaches.",{"name":119,"@type":110,"acceptedAnswer":120},"What two themes structure the discussion throughout the notes?",{"text":121,"@type":113},"The notes emphasize well-defined loss functions that match the problem at hand and uncertainty-aware network approaches.","https://schema.org",{"og:url":83,"og:type":124,"og:title":65,"og:site_name":95,"og:description":67},"article",{"robots":126,"canonical":83},"index,follow",{"doc_id":128,"site_id":62},290421,1789641659,{"code":4,"msg":5,"data":131},{"doc_id":128,"user_id":132,"nickname":92,"user_avatar":133,"doc_module":4,"category_id":39,"category_name":40,"doc_title":65,"doc_description":67,"doc_content":134,"file_id":135,"file_url":136,"file_type":137,"file_size":138,"view_count":52,"is_deleted":4,"is_public":8,"is_downloadable":8,"audit_status":8,"page_count":139,"language":140,"language_code":63,"site_id":62,"html_lang":63,"table_of_contents":141,"faqs":142,"seo_title":143,"seo_description":67,"update_tm":129,"read_time":144,"preview_page_count":4},4398048949847,"https://ap-avatar.wpscdn.com/avatar/400002536579ef2da7f?_k=1778318612642679267","arXiv :2211 .01421v1 [hep-ph] 2 Nov 2022  \nModern Machine Learning for LHC Physicists Tilman Plehna *, Anja Buttera;b , Barry Dillona , and Claudius Krausea;c  \na Institut f¨ur Theoretische Physik, Universitt Heidelberg, Germany b LPNHE, Sorbonne Universit, Universit Paris Cit, CNRS/IN2P3, Paris, France c NHETC, Dept. of Physics and Astronomy, Rutgers University, Piscataway, USA  \nNovember 4, 2022  \nAbstract  \nModern machine learning is transforming particle physics, faster than we can follow, and bullying its way into our numerical tool box. For young researchers it is crucial to stay on top of this development, which means applying cuttingedge methods and tools to the full range of LHC physics problems. These lecture notes are meant to lead students with basic knowledge of particle physics and significant enthusiasm for machine learning to relevant applications as fast as possible. They start with an LHC-specific motivation and a non-standard introduction to neural networks and then cover classification, unsupervised classification, generative networks, and inverse problems. Two themes defining much of the discussion are well-defined loss functions reflecting the problem at hand and uncertainty-aware networks. As part of the applications, the notes include some aspects of theoretical LHC physics. All examples are chosen from particle physics publications of the last few years. Given that these notes will be outdated already at the time of submission, the week of ML4Jets 2022, they will be updated frequently.  \n*plehn@uni-heidelberg.de  \n1 Basics 1  \n1.1 Particle physics ................................................ 1  \n1.1.1 Data recording ............................................ 1  \n1.1.2 Jet and event reconstruction ..................................... 3  \n1.1.3 Simulations .............................................. 4  \n1.1.4 Inference ............................................... 5  \n1.1.5 Uncertainties ............................................. 7  \n1.2 Deep learning ................................................. 8  \n1.2.1 Multivariate classification ...................................... 8  \n1.2.2 Fits and interpolations ........................................ 13  \n1.2.3 Neural networks ........................................... 15  \n1.2.4 Bayesian networks and likelihood loss ................................ 18  \n1.2.5 Amplitude regression ......................................... 20  \n1.2.6 Parton density regression ....................................... 24  \n2 Classification 28  \n2.1 Convolutional networks ............................................ 30  \n2.1.1 Jet images and top tagging ...................................... 30  \n2.1.2 Architecture .............................................. 32  \n2.1.3 Top tagging benchmark ........................................ 36  \n2.1.4 Bayesian CNN ............................................ 38  \n2.2 Capsules .................................................... 40  \n2.2.1 Architecture .............................................. 40  \n2.2.2 Jets and events ............................................ 42  \n2.3 Graphs ..................................................... 44  \n2.3.1 4-Vectors and point clouds ...................................... 44  \n2.3.2 Graph convolutional network ..................................... 46  \n2.3.3 Transformer .............................................. 49  \n2.3.4 Deep sets ............................................... 51  \n2.4 Symmetries and contrastive learning ..................................... 52  \n3 Non-supervised classification 56  \n3.1 Classification without labels ......................................... 56  \n3.2 Anomaly searches ............................................... 59  \n3.2.1 (Variational) autoencoders ...................................... 60  \n3.2.2 Dirichlet-VAE ............................................ 62  \n3.2.3 Normalized autoencoder ....................................... 64  \n4 Generation ","cbCaieAsf6KVkklG","https://ap.wps.com/l/cbCaieAsf6KVkklG","pdf",11219002,128,"English","# Basics\n## Particle physics\n## Deep learning\n# Classification\n## Convolutional networks\n## Capsules\n## Graphs\n## Symmetries and contrastive learning\n# Non-supervised classification\n## Classification without labels\n## Anomaly searches\n# Generation and simulation\n## Variational autoencoders\n## Generative Adversarial Networks\n## Normalizing flows and invertible networks\n# Inverse problems and inference\n## Inversion by reweighting\n## Conditional generative networks\n## Simulation-based inference","[{\"question\":\"What is the purpose of these lecture notes for LHC researchers?\",\"answer\":\"They aim to help students apply modern machine-learning methods to a broad range of LHC physics problems as quickly as possible, starting from basic particle-physics knowledge.\"},{\"question\":\"Which topics from machine learning are covered?\",\"answer\":\"The notes cover neural-network basics, classification, unsupervised classification, generative networks, and inverse problems, including simulation-based approaches.\"},{\"question\":\"What two themes structure the discussion throughout the notes?\",\"answer\":\"The notes emphasize well-defined loss functions that match the problem at hand and uncertainty-aware network approaches.\"}]","Modern Machine Learning for LHC Physicists | PDF",323]