prikaz prve stranice dokumenta Usporedba izvedbi metoda strojnog učenja za klasifikaciju fizikalnih procesa na CMS detektoru
Access restricted to authenticated users
undergraduate thesis
Usporedba izvedbi metoda strojnog učenja za klasifikaciju fizikalnih procesa na CMS detektoru
2022. urn:nbn:hr:179:116004
Filipović, Filip
University of Split
Faculty of Electrical Engineering, Mechanical Engineering and Naval Architecture
Department of Mathematics and Physics

Cite this document

Filipović, F. (2022). Usporedba izvedbi metoda strojnog učenja za klasifikaciju fizikalnih procesa na CMS detektoru (Undergraduate thesis). Split: University of Split, Faculty of Electrical Engineering, Mechanical Engineering and Naval Architecture. Retrieved from https://urn.nsk.hr/urn:nbn:hr:179:116004

Filipović, Filip. "Usporedba izvedbi metoda strojnog učenja za klasifikaciju fizikalnih procesa na CMS detektoru." Undergraduate thesis, University of Split, Faculty of Electrical Engineering, Mechanical Engineering and Naval Architecture, 2022. https://urn.nsk.hr/urn:nbn:hr:179:116004

Filipović, Filip. "Usporedba izvedbi metoda strojnog učenja za klasifikaciju fizikalnih procesa na CMS detektoru." Undergraduate thesis, University of Split, Faculty of Electrical Engineering, Mechanical Engineering and Naval Architecture, 2022. https://urn.nsk.hr/urn:nbn:hr:179:116004

Filipović, F. (2022). 'Usporedba izvedbi metoda strojnog učenja za klasifikaciju fizikalnih procesa na CMS detektoru', Undergraduate thesis, University of Split, Faculty of Electrical Engineering, Mechanical Engineering and Naval Architecture, accessed 26 April 2024, https://urn.nsk.hr/urn:nbn:hr:179:116004

Filipović F. Usporedba izvedbi metoda strojnog učenja za klasifikaciju fizikalnih procesa na CMS detektoru [Undergraduate thesis]. Split: University of Split, Faculty of Electrical Engineering, Mechanical Engineering and Naval Architecture; 2022 [cited 2024 April 26] Available at: https://urn.nsk.hr/urn:nbn:hr:179:116004

F. Filipović, "Usporedba izvedbi metoda strojnog učenja za klasifikaciju fizikalnih procesa na CMS detektoru", 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:179:116004

Please login to the repository to save this object to your list.
Metadata
TitleUsporedba izvedbi metoda strojnog učenja za klasifikaciju fizikalnih procesa na CMS detektoru
Title (english)Comparison of the performance of machine learning methods for the classification of physical processes in the CMS detector
AuthorFilip Filipović
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
Electrical Engineering
Electronics
Abstract
U sudarima na Velikom sudaraču hadrona (LHC) u Ženevi generiraju se velike količine podatka. Pronalazak određenog signala u tolikoj količini podataka nije lak zadatak. Zbog toga se traže i istražuju napredniji načini za obavljanje tog zadatka. U ovom radu se uspoređuju programske implementacije tri metode strojnog učenja od kojih su dvije novije i slabije istražene (PyKeras i PyTorch) i jedne starije (BDTG) i trenutno najviše korištene za klasifikaciju. Usporedbom s BDTG metodom nastoji se dobiti uvid u mogućnosti PyTorch i PyKeras metoda. Nakon analize podataka, zaključak je da PyKeras i PyTorch metode pokazuju mogućnosti poboljšanja rezultata zadataka klasifikacije u odnosu na BDTG metodu.
Abstract (english)
In the particle collisions at Large Hadron Collider (LHC) in Geneva, Switzerland, large amount of data is generated. Finding certain signal in such vast amount of data is not an easy task. Because of that more advanced ways of doing this task are searched and explored. In this thesis program implementations of three methods of machine learning are compared of which two are newer and less explored (PyKeras and PyTorch) and one older (BDTG) and currently most used for classification. By comparing with BDTG method, it has been tried to obtain insight in capacity of PyTorch and PyKeras methods. After the analysis, the conclusion is that PyKeras and PyTorch methods show possibilities of improvement of classification results in comparison to BDTG method.
Keywords
Keywords (english)
Languagecroatian
URN:NBNurn:nbn:hr:179:116004
Study programmeTitle: Electrical Engineering and Information Technology
Study programme type: university
Study level: undergraduate
Academic / professional title: sveučilišni/a prvostupnik/ prvostupnica (baccalaureus/baccalaurea) inženjer/inženjerka elektrotehnike i informacijske tehnologije (sveučilišni/a prvostupnik/ prvostupnica (baccalaureus/baccalaurea) inženjer/inženjerka elektrotehnike i informacijske tehnologije)
Type of resourceText
File originBorn digital
Access conditionsAccess restricted to authenticated users
Terms of useLicence In copyright icon
Created on2023-05-04 10:58:06