[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-117348-en":3,"doc-seo-117348-105":30,"detail-sidebar-cat-0-en-105":91},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":4,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":27,"seo_description":14,"update_tm":28,"read_time":29},117348,1099514068035,"Ezra","https://ap-avatar.wpscdn.com/davatar_276721f389ce27ea32af1340a28f341c",8,"Research & Report","Machine learning - Chapter III.12 - Introduction and Applications","Machine learning is presented as a mathematical toolbox enabling computers to perform tasks without explicit programming, with a focus on its relevance to accelerator physics. The chapter reviews why the approach has become feasible—especially advances in GPU computing, large shared datasets, new neural network architectures, and improved theoretical understanding—then contrasts traditional programming with learning-from-data. Using a linear regression example, it explains training via cost functions and discusses the importance of matching the problem conditions and data quality. Applications in the PSI accelerator complex are introduced alongside external research centers.","Chapter III.12  \nMachine learning  \nJochem Snuverink  \nPaul Scherrer Institute, Villigen, Switzerland  \nMachine learning (ML) is a powerful new mathematical toolbox that allows for new possibilities in a broad variety of research areas. It enables machines to fulfill tasks without being explicitly programmed. There is no reason to believe why machine learning cannot be applied to particle accelerators. After a short introduction to machine learning, in this chapter the existing applications to particle accelerators are reviewed with examples on the PSI accelerator complex.  \nWhen asking chatGPT [1] about machine learning, it answered (bold by the author):  \nMachine learning is not a hype, but rather a powerful tool that has the potential to revolutionise many industries and fields, including healthcare, finance, transportation, and more.  \nMachine learning has already made significant contributions to many applications, such as image recognition, speech recognition, natural language processing, and recommendation systems. These applications have brought significant benefits to users, making their lives easier and more convenient.  \nMoreover, the use of machine learning is not limited to specific industries or applications. Its flexibility allows it to be applied to a wide range of problems and challenges, making it an attractive tool for many researchers, engineers, and businesses.  \nHowever, it is also important to acknowledge that the use of machine learning requires significant expertise in mathematics, statistics, programming, and domain-specific knowledge. Not all applications may benefit from machine learning, and some may require other techniques or methods.  \nTherefore, while machine learning is not a hype, it is also not a panacea for all problems. Its success depends on many factors, including the quality and quantity of data, the expertise of the users, and the suitability of the problem for machine learning techniques.  \nPerhaps not surprisingly chatGPT is excited about the already made contributions, but at the sametime notes it is only successful when the problem conditions are right. To understand the boundaries when machine learning can be successfully applied is active ongoing and expanding research area. Some examples from Swiss universities and research institutes:  \n– ETH-Z: [https://ml.inf.ethz.ch/](https://ml.inf.ethz.ch/) , [https://ethz.ch/en/news-and-events/eth-news/](https://ethz.ch/en/news-and-events/eth-news/)[ ](https://ethz.ch/en/news-and-events/eth-news/)[news/2020/10/pr-new-centre-for-ai-research.html](news/2020/10/pr-new-centre-for-ai-research.html: 29 new professorships in 2020)[: 29 new professorships in 2020](news/2020/10/pr-new-centre-for-ai-research.html: 29 new professorships in 2020);  \n– EPFL: [https://www.epfl.ch/research/domains/ml/](https://www.epfl.ch/research/domains/ml/) ;  \n– Swiss Data Science centre: [https://datascience.ch/](https://datascience.ch/) .  \nThis chapter should be cited as: Machine learning, J. Snuverink, DOI: 10.23730/CYRSP-2024-003.2131, in: Proceedings of  \nthe Joint Universities Accelerator School (JUAS): Courses and exercises, E. Métral (ed.),  \nCERN Yellow Reports: School Proceedings, CERN-2024-003, DOI: 10.23730/CYRSP-2024-003, p. 2131.  \n© CERN, 2024 . Published by CERN under the Creative Commons Attribution 4.0 license.  \nIt is important to understand the new toolbox and understand when it can be applied to accelerator physics. In this chapter a short introduction on machine learning is made and a few examples from the Paul Scherrer Institute (PSI) on applications to accelerator physics are presented.  \nIII.12.1 Machine learning in one page  \nThe seemingly sudden increase of machine learning and artificial intelligence is a combination of technology factors, which all happened in the last decade: the increase of computational capabilities in particular the development and wide availability of GPUs (graphics processing units) allows for more complicated mod","cbCainvqXeq3c7Mr","https://ap.wps.com/l/cbCainvqXeq3c7Mr","pdf",2972760,1,9,"English","en",105,"# Machine learning\n## Machine learning in one page\n## Definitions and conceptual differences\n## Linear regression as a conceptual example\n## Boundary conditions and suitability for ML\n## Applications to particle accelerators at PSI","[{\"question\":\"What is the main idea of machine learning in this chapter?\",\"answer\":\"Machine learning enables systems to accomplish tasks by learning patterns from input and desired output data rather than relying on explicitly programmed rules.\"},{\"question\":\"Why has machine learning grown rapidly in the last decade?\",\"answer\":\"Key drivers include increased computational power (especially GPUs), wider access to large datasets, new neural network architectures and training paradigms, and improved theoretical understanding of neural networks and optimization methods.\"},{\"question\":\"How is linear regression used to explain the ML approach?\",\"answer\":\"The chapter describes fitting a linear model by defining a cost function (mean square error) and training to approximate the relationship between inputs x and outputs y, yielding an equation that predicts outputs for new data within the valid input domain.\"}]","Machine learning - Chapter III.12 - Introduction and Applications | PDF",1785675301,23,{"code":4,"msg":31,"data":32},"ok",{"site_id":24,"language":23,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":28},"machine-learning-chapter-iii12-introduction-and-applications","",{"@graph":36,"@context":85},[37,54,68],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,51],{"item":41,"name":42,"@type":43,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":47},"https://docshare.wps.com/document/","Document",2,{"item":49,"name":12,"@type":43,"position":50},"https://docshare.wps.com/document/research-report/",3,{"item":52,"name":13,"@type":43,"position":53},"https://docshare.wps.com/document/machine-learning-chapter-iii12-introduction-and-applications/117348/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":62,"encodingFormat":61,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-02",true,{"@type":65,"interactionType":66,"userInteractionCount":4},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"What is the main idea of machine learning in this chapter?","Question",{"text":75,"@type":76},"Machine learning enables systems to accomplish tasks by learning patterns from input and desired output data rather than relying on explicitly programmed rules.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"Why has machine learning grown rapidly in the last decade?",{"text":80,"@type":76},"Key drivers include increased computational power (especially GPUs), wider access to large datasets, new neural network architectures and training paradigms, and improved theoretical understanding of neural networks and optimization methods.",{"name":82,"@type":73,"acceptedAnswer":83},"How is linear regression used to explain the ML approach?",{"text":84,"@type":76},"The chapter describes fitting a linear model by defining a cost function (mean square error) and training to approximate the relationship between inputs x and outputs y, yielding an equation that predicts outputs for new data within the valid input domain.","https://schema.org",{"og:url":52,"og:type":87,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":89,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":92},[93,97,101,105,110,115,120,123,127,130,134],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":46,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":46,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":46,"category_name":117,"show_sort_weight":118,"slug":119},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":121,"slug":122},30,"research-report",{"id":21,"doc_module":4,"doc_module_name":46,"category_name":124,"show_sort_weight":125,"slug":126},"Religion & Spirituality",20,"religion-spirituality",{"id":125,"doc_module":4,"doc_module_name":46,"category_name":128,"show_sort_weight":125,"slug":129},"World Cup","world-cup",{"id":131,"doc_module":4,"doc_module_name":46,"category_name":132,"show_sort_weight":131,"slug":133},10,"Lifestyle","lifestyle",{"id":135,"doc_module":4,"doc_module_name":46,"category_name":136,"show_sort_weight":106,"slug":137},19,"General","general"]