[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-117107-en":3,"doc-seo-117107-105":29,"detail-sidebar-cat-0-en-105":90},{"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":11,"language":21,"language_code":22,"site_id":23,"html_lang":22,"table_of_contents":24,"faqs":25,"seo_title":26,"seo_description":14,"update_tm":27,"read_time":28},117107,4398048949847,"Eliana","https://ap-avatar.wpscdn.com/avatar/400002536579ef2da7f?_k=1778318612642679267",6,"Technology","Practical machine learning with PyTorch - Machine Learning workshop materials","Practical machine learning with PyTorch presents hands-on teaching materials that help participants write and run machine learning code while learning key design and engineering considerations. The materials address gaps between high-level ML understanding and practical implementation, including preprocessing details such as image transforms and data preparation workflows. The workshop focuses on building PyTorch model structures and ML pipelines, supporting classification and regression, and applying neural networks like ANN and CNN to tabular and image data.","Practical machine learning with PyTorch  \nJack Atkinson  1¶ and Jim Denholm  1  \nDOI: 10.21105/jose.00239 Software  \n• Review   \n• Repository   \n• Archive   \nSubmitted: 28 October 2023  \nPublished: 23 June 2024  \nLicense  \nAuthors of papers retain copyright and release the work under a Creative Commons Attribution 4.0 International License (CC BY 4 .0) .  \n1 Institute of Computing for Climate Science, University of Cambridge, UK ¶ Corresponding author  \nSummary  \nIn the last decade machine learning (ML) and deep learning (DL)1 have revolutionised many fields within science, industry, and beyond. Researchers across domains from the physical sciences to the digital humanities are increasingly looking to leverage these tools in their research. Many will be experts within their own domains, but will not have received any training in machine learning.  \nWe have developed, and delivered, a set of materials entitled Practical machine learning with PyTorch, designed to teach participants how to actually write and run ML code in a hands-on fashion whilst also illustrating important design considerations.  \nStatement of need  \nWith the explosion of ML and DL there have been several promising opportunities to apply these techniques in research. There are notable applications across many fields from the physical sciences (Carleo et al., 2019), climate science (Kashinath et al., 2021), to the digital humanities (Gefen et al., 2021) .  \nWhilst there exist many examples of ML code online, it is often in the form of complete codes to be downloaded, read, and run by the user. These are often missing any discussion of theory, the development process, or alternative approaches beyond the scope of the specific example. In contrast, much theoretical ML material addresses high-level concepts without discussing coding considerations or details of how to actually use popular frameworks to implement the models.  \nMany know how ML works in an abstract sense, but will be unfamiliar with lower-level practicalities such as image transforms and other preprocessing techniques required to present data to neural networks. They can describe how something works, but would have no idea where to start if asked to do it. Such practical aspects are ideally learnt through trial-and-error and hands-on experience.  \nMany machine learning frameworks are accessed using a Python framework. One such commonly used framework is PyTorch (Paszke et al., 2019) . Researchers are likely to have experience writing Python code, but not PyTorch.  \nLearning objectives  \nThe key learning objective from this workshop could be simply summarised as:“Provide participants with the ability to develop ML models in PyTorch”.  \nHowever, there are a few subtleties that we wish to highlight. We go beyond the ability to blindly run downloaded code to:  \n1We will use the term ML when talking about both ML and DL in this article  \nAtkinson, & Denholm. (2024) . Practical machine learning with PyTorch. Journal of Open Source Education, 7 (76), 239 . [https://doi.org/10.21105/](https://doi.org/10.21105/ 1)[ 1](https://doi.org/10.21105/ 1)[ ](https://doi.org/10.21105/ 1)jose.00239.  \n• provide an understanding of the structure of a PyTorch model and ML pipeline,• introduce the different functionalities PyTorch might provide,  \n• encourage good research software engineering (RSE) practice, and  \n• exercise careful consideration and understanding of data used for training ML models. With regards to specific ML content we cover:  \n• using ML for both classification and regression,  \n• artificial neural networks (ANNs) and convolutional neural networks (CNNs), and  \n• treatment of both tabular and image data.  \nTeaching materials  \nAll of the teaching materials for this course are available online in a GitHub repository. In addition we have a GitHub pages site as a central resource to point participants to.  \nSlides  \nWe have produced two slide decks for the course, both available online and linked from b","cbCaitzf9vm87KJg","https://ap.wps.com/l/cbCaitzf9vm87KJg","pdf",275503,1,"English","en",105,"# Summary\n## Statement of need\n## Learning objectives\n# Teaching materials\n## Slides\n## Exercises (Jupyter notebooks)","[{\"question\":\"What is the main goal of Practical machine learning with PyTorch?\",\"answer\":\"To provide participants with the ability to develop ML models in PyTorch through hands-on code writing and running, supported by important design considerations.\"},{\"question\":\"Why does the workshop emphasize practical coding beyond online ML examples?\",\"answer\":\"Online code is often complete without discussion of theory, development process, or alternatives, while theoretical materials may omit framework-specific coding and implementation details needed to start from scratch.\"},{\"question\":\"Which kinds of data and ML models does the workshop cover?\",\"answer\":\"It covers classification and regression, artificial neural networks (ANNs) and convolutional neural networks (CNNs), and demonstrates approaches for both tabular and image data.\"}]","Practical machine learning with PyTorch - Machine Learning workshop materials | PDF",1785673790,15,{"code":4,"msg":30,"data":31},"ok",{"site_id":23,"language":22,"slug":32,"title":13,"keywords":33,"description":14,"schema_data":34,"social_meta":85,"head_meta":87,"extra_data":89,"updated_unix":27},"practical-machine-learning-with-pytorch-machine-learning-workshop-materials","",{"@graph":35,"@context":84},[36,53,67],{"@type":37,"itemListElement":38},"BreadcrumbList",[39,43,47,50],{"item":40,"name":41,"@type":42,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":44,"name":45,"@type":42,"position":46},"https://docshare.wps.com/document/","Document",2,{"item":48,"name":12,"@type":42,"position":49},"https://docshare.wps.com/document/technology/",3,{"item":51,"name":13,"@type":42,"position":52},"https://docshare.wps.com/document/practical-machine-learning-with-pytorch-machine-learning-workshop-materials/117107/",4,{"url":51,"name":13,"@type":54,"author":55,"headline":13,"publisher":57,"fileFormat":60,"inLanguage":22,"description":14,"dateModified":61,"datePublished":61,"encodingFormat":60,"isAccessibleForFree":62,"interactionStatistic":63},"DigitalDocument",{"name":9,"@type":56},"Person",{"url":40,"name":58,"@type":59},"DocShare","Organization","application/pdf","2026-08-02",true,{"@type":64,"interactionType":65,"userInteractionCount":4},"InteractionCounter",{"@type":66},"ViewAction",{"@type":68,"mainEntity":69},"FAQPage",[70,76,80],{"name":71,"@type":72,"acceptedAnswer":73},"What is the main goal of Practical machine learning with PyTorch?","Question",{"text":74,"@type":75},"To provide participants with the ability to develop ML models in PyTorch through hands-on code writing and running, supported by important design considerations.","Answer",{"name":77,"@type":72,"acceptedAnswer":78},"Why does the workshop emphasize practical coding beyond online ML examples?",{"text":79,"@type":75},"Online code is often complete without discussion of theory, development process, or alternatives, while theoretical materials may omit framework-specific coding and implementation details needed to start from scratch.",{"name":81,"@type":72,"acceptedAnswer":82},"Which kinds of data and ML models does the workshop cover?",{"text":83,"@type":75},"It covers classification and regression, artificial neural networks (ANNs) and convolutional neural networks (CNNs), and demonstrates approaches for both tabular and image data.","https://schema.org",{"og:url":51,"og:type":86,"og:title":13,"og:site_name":58,"og:description":14},"article",{"robots":88,"canonical":51},"index,follow",{"doc_id":7,"site_id":23},{"code":4,"msg":5,"data":91},[92,96,100,104,109,112,117,122,127,130,134],{"id":20,"doc_module":4,"doc_module_name":45,"category_name":93,"show_sort_weight":94,"slug":95},"Story & Novel",90,"story-novel",{"id":46,"doc_module":4,"doc_module_name":45,"category_name":97,"show_sort_weight":98,"slug":99},"Literature",80,"literature",{"id":52,"doc_module":4,"doc_module_name":45,"category_name":101,"show_sort_weight":102,"slug":103},"Exam",70,"exam",{"id":105,"doc_module":4,"doc_module_name":45,"category_name":106,"show_sort_weight":107,"slug":108},5,"Comic",60,"comic",{"id":11,"doc_module":4,"doc_module_name":45,"category_name":12,"show_sort_weight":110,"slug":111},50,"technology",{"id":113,"doc_module":4,"doc_module_name":45,"category_name":114,"show_sort_weight":115,"slug":116},7,"Healthcare",40,"healthcare",{"id":118,"doc_module":4,"doc_module_name":45,"category_name":119,"show_sort_weight":120,"slug":121},8,"Research & Report",30,"research-report",{"id":123,"doc_module":4,"doc_module_name":45,"category_name":124,"show_sort_weight":125,"slug":126},9,"Religion & Spirituality",20,"religion-spirituality",{"id":125,"doc_module":4,"doc_module_name":45,"category_name":128,"show_sort_weight":125,"slug":129},"World Cup","world-cup",{"id":131,"doc_module":4,"doc_module_name":45,"category_name":132,"show_sort_weight":131,"slug":133},10,"Lifestyle","lifestyle",{"id":135,"doc_module":4,"doc_module_name":45,"category_name":136,"show_sort_weight":105,"slug":137},19,"General","general"]