[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-118325-en":3,"doc-seo-118325-105":30,"detail-sidebar-cat-0-en-105":83},{"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},118325,13056703019404,"Miles","https://ap-avatar.wpscdn.com/davatar_29158cc5080c5b710cf443261637dec0",8,"Research & Report","Intergalactic Machine Learning - Bachelor thesis - Optimization of machine learning for gravitational lensing","Bachelor thesis focusing on optimizing a machine learning model for gravitational lensing, aiming to use estimated roulette amplitudes to support dark matter mass estimation in space. The work extends an earlier NTNU research effort by testing and training multiple hyperparameters and comparing neural network choices, with inception network producing strong results while AlexNet experiments underperformed. The study also outlines an initial attempt to reconstruct dark matter mass but prioritizes algorithm optimization within time constraints.","Department of ICT and Natural  \nsciences  \nAIS2900-bacheloroppgave ingeniørfag  \nIntergalactic Machine Learning  \nAuthor:  \nAhmed Mahammed Aseyr Ervik Lars-Joar  \n21.05.2024  \nPreface  \nThis Bachelor thesis was written by two students from ”Automation and intelligent system” at NTNU ˚Alesund with the goal of optimizing a machine learning algorithm in a research project with the goal of using the estimated roulette amplitudes to be able to then again estimate dark matter in space.  \nThis project brought a lot of new challenges and learning materials which is the reason we first chose to write this as our Bachelor thesis. We would like to extend our gratitude towards our supervisors Ben David Normann and Hans Georg Schaathun for their help and insight. This project would not been possible without their wisdow and guidance.  \nSummary  \nGravitational lensing is an an phenomenon that have gained some attention for being the key to mapping and understanding the mysterious dark matter. This project further develops on an research project from NTNU. The task this time was the optimization of the machine learning algorithm that was developed by earlier group, by testing and training different hyper parameters. This process gave good results with the inception network, other test that was done with the AlexNet did not give the results that was expected. In this project there was also an attempt at trying to estimate the mass of dark matter, but there was not enough time todo both of these tasks. The attempt however was good enough to be the start of something, and with the optimized machine learning algorithm, could lead to estimated roulette amplitudes good enough so the mass can be estimated.  \nContents  \nNotation iv  \nList of Figures v  \n1 Introduction 1  \n1.1 Background ............................... 1  \n1.2 Problem ................................. 1  \n1.3 Cosmology ................................ 3  \n1.3.1 Gravitational lensing ..................... 3  \n1.3.2 Lenses .............................. 6  \n1.3.3 Mass reconstruction ...................... 7  \n1.4 Machine Learning ........................... 10  \n1.4.1 Artificial Neural Networks .................. 10  \n1.4.2 Convolutional Neural Network ............... 11  \n1.4.3 Deep learning .......................... 12  \n1.4.4 Networks ............................. 13  \n1.5 Parameters and Hyper Parameters ................ 14  \n1.6 Previous work with machine learning on Gravitational lensing 16  \n1.7 Going through earlier work ..................... 17  \n1.8 Generating images ........................... 17  \n1.9 Machine learning ............................ 18  \n1.9.1 Why Machine learning .................... 18  \n1.9.2 Choosing network ....................... 19  \n1.9.3 Hyper parameters ....................... 19  \n1.9.4 IDUN ............................... 19  \n1.9.5 Problems with the machine learning code ........ 20  \n1.9.6 Debugging ............................ 21  \n1.10 Experiment ............................... 21  \n1.10.1 Base Results .......................... 21  \n1.10.2 Low Learning Rate ...................... 23  \n1.10.3 High Learning Rate ...................... 24  \n1.10.4 Small number of Epochs ................... 25  \n1.10.5 Bigger number of Epochs .................. 26  \n1.10.6 High drop off rate graphs ..................... 27  \n1.10.7 Low drop off rate ......................... 28  \n1.11 AlexNet ................................. 29  \n1.11.1 Base ................................ 29  \n1.11.2 High Learning Rate ........................ 30  \n1.11.3 More Epochs ........................... 31  \n1.11.4 Other hyper parameters ..................... 32  \n2 Results 33  \n2.1 Takeaways ................................. 33  \n2.2 After using knowledge of testing ..................... 33  \n3 Discussion 36  \n3.0.1 The Machine Learning ...................... 36  \n3.1 Debugging ................................. 37  \n3.2 Finding the mass of dark matter ..................... 38  \n4 Concl","cbCainMhU1FtKgZC","https://ap.wps.com/l/cbCainMhU1FtKgZC","pdf",4352022,1,55,"English","en",105,"# Introduction\n## Background\n## Problem\n## Cosmology\n## Machine Learning\n## Parameters and Hyper Parameters\n## Previous work with machine learning on Gravitational lensing\n## Going through earlier work\n## Generating images\n## Experiment\n# Results\n## Takeaways\n## After using knowledge of testing\n# Discussion\n## Debugging\n## Finding the mass of dark matter\n# Conclusion\n## Machine Learning\n## Cosmology\n## What we learned","[{\"question\":\"Was dark matter mass reconstruction fully completed?\",\"answer\":\"An attempt was made to estimate dark matter mass, but there was not enough time to complete both tasks; the results were treated as a starting point.\"}]","Intergalactic Machine Learning - Bachelor thesis - Optimization of machine learning for gravitational lensing | PDF",1785683064,139,{"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":78,"head_meta":80,"extra_data":82,"updated_unix":28},"intergalactic-machine-learning-bachelor-thesis-optimization-of-machine-learning-for-gravitational-lensing","",{"@graph":36,"@context":77},[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/intergalactic-machine-learning-bachelor-thesis-optimization-of-machine-learning-for-gravitational-lensing/118325/",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],{"name":72,"@type":73,"acceptedAnswer":74},"Was dark matter mass reconstruction fully completed?","Question",{"text":75,"@type":76},"An attempt was made to estimate dark matter mass, but there was not enough time to complete both tasks; the results were treated as a starting point.","Answer","https://schema.org",{"og:url":52,"og:type":79,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":81,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":84},[85,89,93,97,102,107,112,115,120,123,127],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":86,"show_sort_weight":87,"slug":88},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":90,"show_sort_weight":91,"slug":92},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Exam",70,"exam",{"id":98,"doc_module":4,"doc_module_name":46,"category_name":99,"show_sort_weight":100,"slug":101},5,"Comic",60,"comic",{"id":103,"doc_module":4,"doc_module_name":46,"category_name":104,"show_sort_weight":105,"slug":106},6,"Technology",50,"technology",{"id":108,"doc_module":4,"doc_module_name":46,"category_name":109,"show_sort_weight":110,"slug":111},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":113,"slug":114},30,"research-report",{"id":116,"doc_module":4,"doc_module_name":46,"category_name":117,"show_sort_weight":118,"slug":119},9,"Religion & Spirituality",20,"religion-spirituality",{"id":118,"doc_module":4,"doc_module_name":46,"category_name":121,"show_sort_weight":118,"slug":122},"World Cup","world-cup",{"id":124,"doc_module":4,"doc_module_name":46,"category_name":125,"show_sort_weight":124,"slug":126},10,"Lifestyle","lifestyle",{"id":128,"doc_module":4,"doc_module_name":46,"category_name":129,"show_sort_weight":98,"slug":130},19,"General","general"]