prikaz prve stranice dokumenta Optimizacija klasifikacije fizikalnih podataka reguliranjem hiperparametara BDTG metode strojnog učenja.
Access restricted to authenticated users
undergraduate thesis
Optimizacija klasifikacije fizikalnih podataka reguliranjem hiperparametara BDTG metode strojnog učenja.
2022. urn:nbn:hr:179:148693
Sarić, Emilija
University of Split
Faculty of Electrical Engineering, Mechanical Engineering and Naval Architecture
Department of Mathematics and Physics

Cite this document

Sarić, E. (2022). Optimizacija klasifikacije fizikalnih podataka reguliranjem hiperparametara BDTG metode strojnog učenja. (Undergraduate thesis). Split: University of Split, Faculty of Electrical Engineering, Mechanical Engineering and Naval Architecture. Retrieved from https://urn.nsk.hr/urn:nbn:hr:179:148693

Sarić, Emilija. "Optimizacija klasifikacije fizikalnih podataka reguliranjem hiperparametara BDTG metode strojnog učenja.." Undergraduate thesis, University of Split, Faculty of Electrical Engineering, Mechanical Engineering and Naval Architecture, 2022. https://urn.nsk.hr/urn:nbn:hr:179:148693

Sarić, Emilija. "Optimizacija klasifikacije fizikalnih podataka reguliranjem hiperparametara BDTG metode strojnog učenja.." Undergraduate thesis, University of Split, Faculty of Electrical Engineering, Mechanical Engineering and Naval Architecture, 2022. https://urn.nsk.hr/urn:nbn:hr:179:148693

Sarić, E. (2022). 'Optimizacija klasifikacije fizikalnih podataka reguliranjem hiperparametara BDTG metode strojnog učenja.', Undergraduate thesis, University of Split, Faculty of Electrical Engineering, Mechanical Engineering and Naval Architecture, accessed 07 May 2024, https://urn.nsk.hr/urn:nbn:hr:179:148693

Sarić E. Optimizacija klasifikacije fizikalnih podataka reguliranjem hiperparametara BDTG metode strojnog učenja. [Undergraduate thesis]. Split: University of Split, Faculty of Electrical Engineering, Mechanical Engineering and Naval Architecture; 2022 [cited 2024 May 07] Available at: https://urn.nsk.hr/urn:nbn:hr:179:148693

E. Sarić, "Optimizacija klasifikacije fizikalnih podataka reguliranjem hiperparametara BDTG metode strojnog učenja.", 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:179:148693

Please login to the repository to save this object to your list.
Metadata
TitleOptimizacija klasifikacije fizikalnih podataka reguliranjem hiperparametara BDTG metode strojnog učenja.
Title (english)Optimization of classification of physical data by regulating hyperparameters of the BDTG method of machine learning
AuthorEmilija Sarić
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
Zbog potrebe za obradom sve većih količina podataka, strojno učenje danas ima sve veći značaj i primjenu. Metodama strojnog učenja nastoje se izgraditi efektivni modeli koji na temelju usvojenih informacija mogu predviđati i donositi odluke. Na taj se način, kako bi se postigli najbolji mogući rezultati, metode optimiziraju i prilagođavaju svakom novom skupu podataka. Optimizacija metode podrazumijeva izbor najboljeg modela i pronalazak najboljih hiperparametara metode. Hiperparametri označavaju vrijednosti modela koje se specificiraju kako bi se povećala efikasnost metode. Specifikacija hiperparametara može se izvoditi ručno, ali zbog neefikasnosti samog postupka sve se više koriste razni algoritmi automatske optimizacije. U ovom rada je provedena hiperparametarska optimizacija BDTG (engl. Boosted Decision Tree Gradient) metode strojnog učenja na danim ulaznim podacima pomoću jedne od automatskih metoda optimizacije.
Abstract (english)
Due to increasing volume of data that is necessary to analyse every day, machine learning has an ever-increasing importance and application. Machine learning methods are used to build effective models that can predict and make decisions based on the acquired information. Therefore, in order to achieve the best possible results, the methods are optimized and adapted to each new dataset. Method optimization implies finding the optimal model and finding the best hyperparameters of the model. Hyperparameters are model values that are specified to improve model performance. The specification of hyperparameters can be performed manually, but due to the inefficiency of the procedure itself, various automatic optimization algorithms are increasingly used. In this thesis, hyperparametric optimization of the BDTG (Boosted Decision Tree Gradient) machine learning method has been performed on a given dataset by using one of the automatic optimization algorithms.
Keywords
Keywords (english)
Languagecroatian
URN:NBNurn:nbn:hr:179:148693
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 on2023-06-30 10:36:25