prikaz prve stranice dokumenta Pronalaženje fizičkih jednadžbi uz pomoć umjetne inteligencije
Access restricted to authenticated users
undergraduate thesis
Pronalaženje fizičkih jednadžbi uz pomoć umjetne inteligencije
Split: University of Split, Faculty of Electrical Engineering, Mechanical Engineering and Naval Architecture, 2022. urn:nbn:hr:179:618225
Lunić, Vedran
University of Split
Faculty of Electrical Engineering, Mechanical Engineering and Naval Architecture
Department of Mathematics and Physics

Institutional repository: Repository of the Faculty of Electrical Engineering, Mechanical Engineering and Naval Architecture

Cite this document

Lunić, V. (2022). Pronalaženje fizičkih jednadžbi uz pomoć umjetne inteligencije (Undergraduate thesis). Split: University of Split, Faculty of Electrical Engineering, Mechanical Engineering and Naval Architecture. Retrieved from https://urn.nsk.hr/urn:nbn:hr:179:618225

Lunić, Vedran. "Pronalaženje fizičkih jednadžbi uz pomoć umjetne inteligencije." Undergraduate thesis, University of Split, Faculty of Electrical Engineering, Mechanical Engineering and Naval Architecture, 2022. https://urn.nsk.hr/urn:nbn:hr:179:618225

Lunić, Vedran. "Pronalaženje fizičkih jednadžbi uz pomoć umjetne inteligencije." Undergraduate thesis, University of Split, Faculty of Electrical Engineering, Mechanical Engineering and Naval Architecture, 2022. https://urn.nsk.hr/urn:nbn:hr:179:618225

Lunić, V. (2022). 'Pronalaženje fizičkih jednadžbi uz pomoć umjetne inteligencije', Undergraduate thesis, University of Split, Faculty of Electrical Engineering, Mechanical Engineering and Naval Architecture, accessed 18 February 2025, https://urn.nsk.hr/urn:nbn:hr:179:618225

Lunić V. Pronalaženje fizičkih jednadžbi uz pomoć umjetne inteligencije [Undergraduate thesis]. Split: University of Split, Faculty of Electrical Engineering, Mechanical Engineering and Naval Architecture; 2022 [cited 2025 February 18] Available at: https://urn.nsk.hr/urn:nbn:hr:179:618225

V. Lunić, "Pronalaženje fizičkih jednadžbi uz pomoć umjetne inteligencije", Undergraduate thesis, University of Split, Faculty of Electrical Engineering, Mechanical Engineering and Naval Architecture, Split, 2022. Available at: https://urn.nsk.hr/urn:nbn:hr:179:618225

Metadata
TitlePronalaženje fizičkih jednadžbi uz pomoć umjetne inteligencije
Title (english)Finding physical equations with the help of artificial intelligence
AuthorVedran Lunić
MentorDamir Lelas https://orcid.org/0000-0002-8269-5760 (mentor)
GranterUniversity of Split
Faculty of Electrical Engineering, Mechanical Engineering and Naval Architecture
(Department of Mathematics and Physics)
Split
Defense date and country2022-09-19, Croatia
Scientific / art field,
discipline and subdiscipline		TECHNICAL SCIENCES
Computing
Abstract
Tema ovog rada je izrada dva modela strojnog učenja koji će pomoću dobivenih varijabli i rješenja pronaći matematički izraz koji ih povezuje. Glavni cilj je onda ove modele iskoristiti za otkrivanje fizičkih zakonitosti u danim procesima. Opisana je povijest umjetne inteligencije i strojnog učenja, te njene dosadašnje primjene u fizici. Ukratko su opisana PyCharm i Google Colaboratory okruženja. Detaljnije su objašnjene metode linearne i simboličke regresije korištene pri izradi gore navedenih modela. Modeli su realizirani u Google Colaboratory okruženju. Model linearne regresije je za cilj imao otkriti izraz za visinu kod slobodnog pada objekta s početnom brzinom, dok je model simboličke regresije imao za cilj otkriti izraz za horizontalni pomak kod kosog hica.
Abstract (english)
The topic of this bachelor thesis is the creation of two machine learning models that will use the variables and solutions to find a mathematical expression that connects them. The main goal is to use these models to discover physical laws in given processes. The history of artificial intelligence and machine learning, as well as its current application in physics, is described. PyCharm and Google Collaboratory environments are briefly described. The linear and symbolic regression methods used in creating the above models are explained in more detail. The models were realized in the Google Collaboratory environment. The linear regression model aimed to find an expression for the height of a free-falling object with an initial velocity, while the symbolic regression model aimed to find an expression for the horizontal displacement of a ballistic motion.
Keywords
Keywords (english)
Languagecroatian
URN:NBNurn:nbn:hr:179:618225
Study programmeTitle: Computing
Study programme type: university
Study level: undergraduate
Academic / professional title: sveučilišni/a prvostupnik/ prvostupnica (baccalaureus/baccalaurea) inženjer/inženjerka računarstva (sveučilišni/a prvostupnik/ prvostupnica (baccalaureus/baccalaurea) inženjer/inženjerka računarstva)
Type of resourceText
File originBorn digital
Access conditionsAccess restricted to authenticated users
Terms of useLicence In copyright icon
Created on2023-06-01 08:30:21