prikaz prve stranice dokumenta Bayesovsko duboko učenje za klasifikaciju teksta
No public access
master's thesis
Bayesovsko duboko učenje za klasifikaciju teksta
Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing, 2019. urn:nbn:hr:168:759583
Šajatović, Antonio
University of Zagreb
Faculty of Electrical Engineering and Computing

Institutional repository: FER Repository

Cite this document

Šajatović, A. (2019). Bayesovsko duboko učenje za klasifikaciju teksta (Master's thesis). Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing. Retrieved from https://urn.nsk.hr/urn:nbn:hr:168:759583

Šajatović, Antonio. "Bayesovsko duboko učenje za klasifikaciju teksta." Master's thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, 2019. https://urn.nsk.hr/urn:nbn:hr:168:759583

Šajatović, Antonio. "Bayesovsko duboko učenje za klasifikaciju teksta." Master's thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, 2019. https://urn.nsk.hr/urn:nbn:hr:168:759583

Šajatović, A. (2019). 'Bayesovsko duboko učenje za klasifikaciju teksta', Master's thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, accessed 14 January 2025, https://urn.nsk.hr/urn:nbn:hr:168:759583

Šajatović A. Bayesovsko duboko učenje za klasifikaciju teksta [Master's thesis]. Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing; 2019 [cited 2025 January 14] Available at: https://urn.nsk.hr/urn:nbn:hr:168:759583

A. Šajatović, "Bayesovsko duboko učenje za klasifikaciju teksta", Master's thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, Zagreb, 2019. Available at: https://urn.nsk.hr/urn:nbn:hr:168:759583

Metadata
TitleBayesovsko duboko učenje za klasifikaciju teksta
Title (english)Bayesian Deep Learning for Text Classification
AuthorAntonio Šajatović
MentorJan Šnajder (mentor)
Committee memberJan Šnajder (predsjednik povjerenstva)
Committee memberBojana Dalbelo-Bašić (član povjerenstva)
Committee memberMarko Čupić (član povjerenstva)
GranterUniversity of Zagreb
Faculty of Electrical Engineering and Computing
Zagreb
Defense date and country2019-07-11, Croatia
Scientific / art field,
discipline and subdiscipline		TECHNICAL SCIENCES
Computing
Abstract
Modeli dubokog učenja postižu vrhunske performanse u klasifikaciji teksta, jednom od zadataka u obradi prirodnog jezika. Međutim, kako ovi modeli koriste točkovne procjene svojih parametara, oni nisu u stanju modelirati prediktivnu nesigurnost. Na duboko učenje je primijenjena Bayesova teorija vjerojatnosti, što je rezultiralo područjem koje se zove Bayesovsko duboko učenje, omogućujući dubokim modelima da modeliraju nesigurnost na principijelan način. Cilj ovog rada bio je ispitati performanse Bayesovih dubokih modula za klasifikaciju teksta i nove primjene nesigurnosti modela. Bayes by Backprop metoda korištena je za implementaciju nekoliko modela klasifikacije teksta, koji su postigli performanse usporedive s modelima s točkovnim procjenama parametara. Modeli su evaluirani na tri različita skupa podataka za klasifikaciju na engleskom jeziku. Naposljetku, prediktivna nesigurnost koja se upotrebljava za suzdržavanje od klasifikacije uspoređena je s jednostavnim bazičnim pristupom u eksperimentima selektivne klasifikacije.
Abstract (english)
Deep learning models achieve state of the art performance in text classification, a task in natural language processing. However, as these models use point estimates of their parameters, they are not able to model the predictive uncertainty. Bayesian probability theory was applied to deep learning, resulting in a field called Bayesian deep learning, enabling deep learning models to incorporate uncertainty in a principled way. To goal of this thesis was to examine the performance of Bayesian deep models for text classification and novel applications of model uncertainty. The Bayes by Backprop method was used to implement several text classification models that were shown to achieve performance comparable with point estimate models. The models were evaluated on three different English text classification datasets. Finally, predictive uncertainty used to abstain from classification was compared with a simple baseline approach in the selective classification experiments.
Keywords
Keywords (english)
Languageenglish
URN:NBNurn:nbn:hr:168:759583
Study programmeTitle: Computing
Study programme type: university
Study level: graduate
Academic / professional title: magistar/magistra inženjer/inženjerka računarstva (magistar/magistra inženjer/inženjerka računarstva)
Type of resourceText
File originBorn digital
Access conditionsClosed access
Terms of useLicence In copyright icon
Public note
Created on2020-01-07 22:14:10