[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-118295-en":3,"doc-seo-118295-105":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},118295,7971461740886,"Theodore","https://ap-avatar.wpscdn.com/davatar_3d24733baf745e90a7e4bdd5f77d97b2",6,"Technology","Exploring the Portenta H7 for embedded machine learning - Bachelor thesis","The project studies the capabilities of the Portenta H7 microcontroller for automated embedded learning applications, with a focus on utilizing the device’s two cores. It builds on an existing embedded machine learning software that originally worked with only one core. The work is driven by TinyML potential for small microcontrollers and includes processes and experiments to evaluate performance. Results rely on adapting and validating the base code for dual-core usage.","EXPLORING THE PORTENTA H7 FOR EMBEDDED MACHINE LEARNING  \nROGER BAUTISTA TORRENT  \nThesis supervisor: FELIX FREITAG (Department of Computer Architecture) Degree: Bachelor's Degree in Informatics Engineering (Computing)  \nBachelor's thesis Facultat d'Informàtica de Barcelona (FIB) Universitat Politècnica de Catalunya (UPC) -BarcelonaTech  \n16/05/2024  \nTitle: Exploring the Portenta H7 for embedded machine learning  \nAuthor: Roger Bautista i Torrent  \nDirector: Felix Freitag  \nDate: May 9, 2024  \nAbstract  \nThe main objective of this project is to study the capabilities of the Portenta H7 for use in automated embedded learning applications, mainly the use of the Portenta’s two cores. Our base is a previously developed software to do embedded machine learning with only one of the available cores. This study is motivated by the potential of tiny machine learning technologies on small microcontrollers. In this project, we study and test the capabilities of this microcontroller for adapting the machine learning application on which we are based for usage with two cores.  \nT´ıtol: Exploring the Portenta H7 for embedded machine learning Autor: Roger Bautista i Torrent  \nDirector: Felix Freitag  \nData: 9 de maig de 2024  \nAbstract  \nL’objectiu principal d’aquest projecte s l’estudi de les capacitats del Portenta H7 per alseu us en les aplicacions d’aprenentatge automatitzades integrades, principalment en el s dels seus dos nuclis. Basant-nos en un programari prviament utilitzat per a fer aprenentatge automatitzat en un nic nucli. Aquest estudi ve motivat pel potencial de les noves tecnologies d’aprenentatge automtic en petits microcontroladors. En aquest documents’explicar tot el procs fet servir per a estudiar i provar les capacitats d’aquest microcontrolador mentre s’adapta el codi del qual ens basem per al seu s per a dos nuclis.  \nT´ıtulo: Exploring the Portenta H7 for embedded machine learning Autor: Roger Bautista i Torrent  \nDirector: Felix Freitag  \nFecha: 9 de mayo de 2024  \nAbstract  \nEl objetivo principal de este proyecto es el estudio de las capacidades del Portenta H7 para su uso en las aplicaciones de aprendizaje automatizado integrado, principalmente en el uso de los dos cores. Basandonos en un software previamente usado para hacer aprendizaje automatizado integrado con solo un nico nucleo. Este estudio viene impulsado porel potencialen las nuevas tecnologias de machine learning para peque os microcontroladores. En este documento se explicar todo el proceso usado para estudiar y probarlas capacidades de este microcontrolador mientras se adaptar el codigo en el cual nos basamos para su uso para dos cores.  \nCONTENTS  \nCHAPTER 1. Context .............................. 1  \n1.1. Introduction ................................... 1  \n1.2. Terms and Concepts .............................. 1  \n1.3. Problem to be solved .............................. 1  \n1.4. Stakeholders .................................. 2  \nCHAPTER 2. Justification ........................... 3  \n2.1. TinyML ...................................... 3  \n2.2. Portenta H7 ................................... 3  \nCHAPTER 3. Scope ............................... 5  \n3.1. Objectives and sub-objectives ......................... 5  \n3.2. Potential obstacles ............................... 5  \n3.3. Requirements .................................. 5  \n3.3.1. Functional requirements ........................ 5  \n3.3.2. Non-functional requirements ..................... 6  \nCHAPTER 4. Methodology .......................... 7  \nCHAPTER 5. Project schedule ........................ 9  \n5.1. Task description ................................ 9  \n5.1.1. PM: Project Management ....................... 9  \n5.1.2. D: Documentation ........................... 10  \n5.1.3. LP: Learning Portenta H7 ....................... 10  \n5.1.4. PR: Previous Research ........................ 10  \n5.1.5. DC: Dual-core Implementation .................... 11  \n5.1.6. C: Comparison with other microcontroller","cbCaisYJuirU7aBY","https://ap.wps.com/l/cbCaisYJuirU7aBY","pdf",679223,1,92,"English","en",105,"# Chapter 1. Context\n## 1.1. Introduction\n## 1.2. Terms and Concepts\n## 1.3. Problem to be solved\n## 1.4. Stakeholders\n# Chapter 2. Justification\n## 2.1. TinyML\n## 2.2. Portenta H7\n# Chapter 3. Scope\n## 3.1. Objectives and sub-objectives\n## 3.2. Potential obstacles\n## 3.3. Requirements\n## 3.3.1. Functional requirements\n## 3.3.2. Non-functional requirements\n# Chapter 4. Methodology\n# Chapter 5. Project schedule\n## 5.1. Task description\n## 5.1.1. PM: Project Management\n## 5.1.2. D: Documentation\n## 5.1.3. LP: Learning Portenta H7\n## 5.1.4. PR: Previous Research\n## 5.1.5. DC: Dual-core Implementation\n## 5.1.6. C: Comparison with other microcontrollers\n# Chapter 6. Resources\n## 6.1. Human Resources\n## 6.2. Software\n## 6.3. Hardware\n# Chapter 7. Risk Management\n# Chapter 8. Budget\n## 8.1. Staff costs\n## 8.2. Resource costs\n## 8.2.1. Software\n## 8.2.2. Hardware\n## 8.3. Contingencies\n## 8.4. Total Cost\n# Chapter 9. Sustainability\n## 9.1. Autoavaluation\n## 9.2. Economic\n## 9.3. Environmental\n## 9.4. Social\n# Chapter 10.Background\n## 10.1.Embedded Learning and TinyML\n## 10.1.1. Basic explanation\n## 10.1.2. Workflow\n## 10.2.Software\n## 10.2.1. Arduino IDE\n## 10.2.2. Visual Studio Code and PlatformIO\n## 10.3.Microcontrollers\n## 10.3.1. Portenta H7\n## 10.3.2. Nano 33 BLE\n## 10.4.Neural Networks\n## 10.4.1. Autoencoder\n## 10.4.2. Convolutional Neural Network\n# Chapter 11.Application analysis\n## 11.1. Component analysis\n## 11.1.1. Microcontroller code\n## 11.1.2. Server code\n## 11.2. Insights","[{\"question\":\"What is the main goal of the project involving Portenta H7?\",\"answer\":\"To study the Portenta H7’s capabilities for automated embedded learning applications, especially when using both available cores.\"},{\"question\":\"How does the project start from a prior implementation?\",\"answer\":\"It uses a previously developed embedded machine learning software that ran on only one core, then adapts it for dual-core execution.\"},{\"question\":\"Why is TinyML relevant to this study?\",\"answer\":\"The work is motivated by the promise of TinyML technologies for running learning tasks on small microcontrollers like the Portenta H7.\"}]","Exploring the Portenta H7 for embedded machine learning - Bachelor thesis | PDF",1785682859,232,{"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},"exploring-the-portenta-h7-for-embedded-machine-learning-bachelor-thesis","",{"@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/technology/",3,{"item":52,"name":13,"@type":43,"position":53},"https://docshare.wps.com/document/exploring-the-portenta-h7-for-embedded-machine-learning-bachelor-thesis/118295/",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 goal of the project involving Portenta H7?","Question",{"text":75,"@type":76},"To study the Portenta H7’s capabilities for automated embedded learning applications, especially when using both available cores.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How does the project start from a prior implementation?",{"text":80,"@type":76},"It uses a previously developed embedded machine learning software that ran on only one core, then adapts it for dual-core execution.",{"name":82,"@type":73,"acceptedAnswer":83},"Why is TinyML relevant to this study?",{"text":84,"@type":76},"The work is motivated by the promise of TinyML technologies for running learning tasks on small microcontrollers like the Portenta H7.","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},[93,97,101,105,110,113,118,123,128,131,135],{"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":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":111,"slug":112},50,"technology",{"id":114,"doc_module":4,"doc_module_name":46,"category_name":115,"show_sort_weight":116,"slug":117},7,"Healthcare",40,"healthcare",{"id":119,"doc_module":4,"doc_module_name":46,"category_name":120,"show_sort_weight":121,"slug":122},8,"Research & Report",30,"research-report",{"id":124,"doc_module":4,"doc_module_name":46,"category_name":125,"show_sort_weight":126,"slug":127},9,"Religion & Spirituality",20,"religion-spirituality",{"id":126,"doc_module":4,"doc_module_name":46,"category_name":129,"show_sort_weight":126,"slug":130},"World Cup","world-cup",{"id":132,"doc_module":4,"doc_module_name":46,"category_name":133,"show_sort_weight":132,"slug":134},10,"Lifestyle","lifestyle",{"id":136,"doc_module":4,"doc_module_name":46,"category_name":137,"show_sort_weight":106,"slug":138},19,"General","general"]