prikaz prve stranice dokumenta Rješavanje jednodimenzionalne Poissonove diferencijalne jednadžbe metodama strojnog učenja
Access restricted to students and staff of home institution
undergraduate thesis
Rješavanje jednodimenzionalne Poissonove diferencijalne jednadžbe metodama strojnog učenja
2021. urn:nbn:hr:179:123606
Tadin, Marin
University of Split
Faculty of Electrical Engineering, Mechanical Engineering and Naval Architecture
Department of Electronics and Computing

Cite this document

Tadin, M. (2021). Rješavanje jednodimenzionalne Poissonove diferencijalne jednadžbe metodama strojnog učenja (Undergraduate thesis). Retrieved from https://urn.nsk.hr/urn:nbn:hr:179:123606

Tadin, Marin. "Rješavanje jednodimenzionalne Poissonove diferencijalne jednadžbe metodama strojnog učenja." Undergraduate thesis, University of Split, Faculty of Electrical Engineering, Mechanical Engineering and Naval Architecture, 2021. https://urn.nsk.hr/urn:nbn:hr:179:123606

Tadin, Marin. "Rješavanje jednodimenzionalne Poissonove diferencijalne jednadžbe metodama strojnog učenja." Undergraduate thesis, University of Split, Faculty of Electrical Engineering, Mechanical Engineering and Naval Architecture, 2021. https://urn.nsk.hr/urn:nbn:hr:179:123606

Tadin, M. (2021). 'Rješavanje jednodimenzionalne Poissonove diferencijalne jednadžbe metodama strojnog učenja', Undergraduate thesis, University of Split, Faculty of Electrical Engineering, Mechanical Engineering and Naval Architecture, accessed 29 March 2023, https://urn.nsk.hr/urn:nbn:hr:179:123606

Tadin M. Rješavanje jednodimenzionalne Poissonove diferencijalne jednadžbe metodama strojnog učenja [Undergraduate thesis]. Split: University of Split, Faculty of Electrical Engineering, Mechanical Engineering and Naval Architecture; 2021 [cited 2023 March 29] Available at: https://urn.nsk.hr/urn:nbn:hr:179:123606

M. Tadin, "Rješavanje jednodimenzionalne Poissonove diferencijalne jednadžbe metodama strojnog učenja", Undergraduate thesis, University of Split, Faculty of Electrical Engineering, Mechanical Engineering and Naval Architecture, Split, 2021. Available at: https://urn.nsk.hr/urn:nbn:hr:179:123606

Please login to the repository to save this object to your list.
Metadata
TitleRješavanje jednodimenzionalne Poissonove diferencijalne jednadžbe metodama strojnog učenja
Title (english)Machine learning based 1D Poisson equation solver
AuthorMarin Tadin
MentorVicko Dorić (mentor)
GranterUniversity of Split
Faculty of Electrical Engineering, Mechanical Engineering and Naval Architecture
(Department of Electronics and Computing)
Split
Defense date and country2021-03-05, Croatia
Scientific / art field,
discipline and subdiscipline		TECHNICAL SCIENCES
Computing
Abstract
Strojno učenje je grana znanosti koja se bavi proučavanjem računalnih algoritama koji se unaprjeđuju automatski. Neuronske mreže su najrasprostranjeniji tip modela, te je cilj ovog završnog rada istraživanje primjene metoda strojnog učenja na rješavanje diferencijalnih jednadžbi te treniranje neuronske mreže i generacija modela koji uspješno i precizno predviđa rješenje jednodimenzionalne Poissonove diferencijalne jednadžbe. U sklopu toga cilja napisan je fleksibilan generator skupa podataka za treniranje i izgrađen je sekvencijalni model. Taj model je uz naknadne preinake poprimio još jedan oblik. Prvi model je prihvaćao ulazne parametre x i 𝜌/𝜀 , dok drugi model uz te vrijednosti uzima i granične vrijednosti 𝜑0 i 𝜑𝐿 .
Abstract (english)
Machine learning is a branch of science that deals with the study of computer algorithms that are improved automatically. Neural networks are the most common type of model, and the aim of this work is to investigate the application of machine learning methods to solve differential equations and to train a neural network to generate a model that successfully and accurately predicts the solution of the one-dimensional Poisson differential equation. As part of this goal, a flexible training data set generator was written and a sequential model was built. This model took another form with subsequent modifications. The first model accepted the input parameters x and 𝜌/𝜀 , while the second model accepts additional input values in the form of the limit values 𝜑0 and 𝜑𝐿 .
Keywords
Keywords (english)
Languagecroatian
URN:NBNurn:nbn:hr:179:123606
Study programmeTitle: Computing
Study programme type: professional
Study level: undergraduate
Academic / professional title: stručni/a prvostupnik/ prvostupnica inženjer/inženjerka računarstva (stručni/a prvostupnik/ prvostupnica inženjer/inženjerka računarstva)
Type of resourceText
File originBorn digital
Access conditionsAccess restricted to students and staff of home institution
Terms of useLicence In copyright icon
Created on2021-12-10 11:13:05