prikaz prve stranice dokumenta Primjena grafova za regularizaciju neuronskih mreža
  Download
PDF 1.76 MB
master's thesis
Primjena grafova za regularizaciju neuronskih mreža
Osijek: Josip Juraj Strossmayer University of Osijek, Department of Mathematics, 2020. urn:nbn:hr:126:607301
Židov, Ivan
Josip Juraj Strossmayer University of Osijek
Department of Mathematics
Chair of Applied Mathematics and Computer Science
Computer Science and Machine Learning Research Group

Institutional repository: Repository of School of Applied Mathematics and Informatics

Cite this document

Židov, I. (2020). Primjena grafova za regularizaciju neuronskih mreža (Master's thesis). Osijek: Josip Juraj Strossmayer University of Osijek, Department of Mathematics. Retrieved from https://urn.nsk.hr/urn:nbn:hr:126:607301

Židov, Ivan. "Primjena grafova za regularizaciju neuronskih mreža." Master's thesis, Josip Juraj Strossmayer University of Osijek, Department of Mathematics, 2020. https://urn.nsk.hr/urn:nbn:hr:126:607301

Židov, Ivan. "Primjena grafova za regularizaciju neuronskih mreža." Master's thesis, Josip Juraj Strossmayer University of Osijek, Department of Mathematics, 2020. https://urn.nsk.hr/urn:nbn:hr:126:607301

Židov, I. (2020). 'Primjena grafova za regularizaciju neuronskih mreža', Master's thesis, Josip Juraj Strossmayer University of Osijek, Department of Mathematics, accessed 25 January 2025, https://urn.nsk.hr/urn:nbn:hr:126:607301

Židov I. Primjena grafova za regularizaciju neuronskih mreža [Master's thesis]. Osijek: Josip Juraj Strossmayer University of Osijek, Department of Mathematics; 2020 [cited 2025 January 25] Available at: https://urn.nsk.hr/urn:nbn:hr:126:607301

I. Židov, "Primjena grafova za regularizaciju neuronskih mreža", Master's thesis, Josip Juraj Strossmayer University of Osijek, Department of Mathematics, Osijek, 2020. Available at: https://urn.nsk.hr/urn:nbn:hr:126:607301

Metadata
TitlePrimjena grafova za regularizaciju neuronskih mreža
Title (english)Application of Graphs for Neural Networks Regularization
AuthorIvan Židov
MentorDomagoj Ševerdija (mentor)
Committee memberDomagoj Matijević (predsjednik povjerenstva)
Committee memberDomagoj Ševerdija (član povjerenstva)
Committee memberSlobodan Jelić (član povjerenstva)
GranterJosip Juraj Strossmayer University of Osijek
Department of Mathematics
(Chair of Applied Mathematics and Computer Science)
(Computer Science and Machine Learning Research Group)
Osijek
Defense date and country2020-10-30, Croatia
Scientific / art field,
discipline and subdiscipline		NATURAL SCIENCES
Mathematics
Applied Mathematics and Mathematical Modeling
Abstract
U današnje vrijeme, upotreba modela temeljenih na neuronskih mreža postala je sve češća, jer nerijetko postižu bolje rezultate od klasičnih metoda. Kako bi modeli bili primijenivi na stvarnim podacima, potrebno je spriječiti prenaučenost nad podacima za treniranje. To se postiže regularizacijom neuronskih mreža. Jedna od tehnika je i graf-regularizacija o kojoj smo govorili u ovom radu. U prvom dijelu rada, objasnili smo osnove strojnog učenja i osnove teorije grafova, dok smo u drugom dijelu definirali graf-regularizaciju i primjenili ju na konkretnom primjeru.
Abstract (english)
Nowadays, the use of models based on neural networks has become more common, as they often achieve better results than classical methods. In order for the models to be applicable to real data, it is necessary to prevent over-fitting over training data. This is achieved by regularizing neural networks. One of the techniques is graph-regularization, which we talked about in this paper. In the first part of the paper, we explained the basics of machine learning and the basics of graph theory, while in the second part we defined graph-regularization and applied it to a concrete example.
Keywords
Keywords (english)
Languagecroatian
URN:NBNurn:nbn:hr:126:607301
Study programmeTitle: Mathematics; specializations in: Financial and Statistical Mathematics, Mathematics and Computer Science, Industrial and Applied Mathematics
Course: Financial and Statistical Mathematics
Study programme type: university
Study level: graduate
Academic / professional title: magistar/magistra matematike (magistar/magistra matematike)
Type of resourceText
File originBorn digital
Access conditionsOpen access
Terms of useLicence In copyright icon
Created on2020-11-02 11:42:52