prikaz prve stranice dokumenta Otkrivanje izvandistribucijskih podataka analizom izlaza dubokog modela
No public access
undergraduate thesis
Otkrivanje izvandistribucijskih podataka analizom izlaza dubokog modela
Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing, 2018. urn:nbn:hr:168:925571
Kovač, Bruno
University of Zagreb
Faculty of Electrical Engineering and Computing

Institutional repository: FER Repository

Cite this document

Kovač, B. (2018). Otkrivanje izvandistribucijskih podataka analizom izlaza dubokog modela (Undergraduate thesis). Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing. Retrieved from https://urn.nsk.hr/urn:nbn:hr:168:925571

Kovač, Bruno. "Otkrivanje izvandistribucijskih podataka analizom izlaza dubokog modela." Undergraduate thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, 2018. https://urn.nsk.hr/urn:nbn:hr:168:925571

Kovač, Bruno. "Otkrivanje izvandistribucijskih podataka analizom izlaza dubokog modela." Undergraduate thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, 2018. https://urn.nsk.hr/urn:nbn:hr:168:925571

Kovač, B. (2018). 'Otkrivanje izvandistribucijskih podataka analizom izlaza dubokog modela', Undergraduate thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, accessed 02 June 2024, https://urn.nsk.hr/urn:nbn:hr:168:925571

Kovač B. Otkrivanje izvandistribucijskih podataka analizom izlaza dubokog modela [Undergraduate thesis]. Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing; 2018 [cited 2024 June 02] Available at: https://urn.nsk.hr/urn:nbn:hr:168:925571

B. Kovač, "Otkrivanje izvandistribucijskih podataka analizom izlaza dubokog modela", Undergraduate thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, Zagreb, 2018. Available at: https://urn.nsk.hr/urn:nbn:hr:168:925571

Metadata
TitleOtkrivanje izvandistribucijskih podataka analizom izlaza dubokog modela
Title (english)Discovery of Out-of-Distribution Data by Analyzing Predictions of a Deep Model
AuthorBruno Kovač
MentorSiniša Šegvić (mentor)
Committee memberSiniša Šegvić (predsjednik povjerenstva)
Committee memberMarin Oršić (član povjerenstva)
Committee memberIvan Krešo (član povjerenstva)
GranterUniversity of Zagreb
Faculty of Electrical Engineering and Computing
Zagreb
Defense date and country2018-07-13, Croatia
Scientific / art field,
discipline and subdiscipline		TECHNICAL SCIENCES
Computing
Abstract
Konvolucijske neuronske mreže danas su često korištene za klasifikacijsku ulaznih podataka u pojedine moguće razrede za koje je model prethodno istreniran. Neovisno o testnom podatku, model će uvijek s određenom sigurnošću predvidjeti pripradnost ulaza u jedan od klasifikacijskih razreda. Ključna problematika ovog pristupa je nemogućnost otkrivanja ulaznih podataka za koje će model najvjerojatnije pogriješiti. Upravo zbog toga potrebno je otkriti izvandistribucijske podatke dovedene na ulaz modela, a to činimo analizom njegovog izlaza. Kod takvih podataka nikad ne možemo sigurno tvrditi jesu li dijelom distribucije na kojoj je model treniran ili su vandistribucijski, no vjerojatnost detekcije izvandistribucijskih podataka moguće je odrediti na više načina, npr. korištenjem AUROC i AUPR površina.
Abstract (english)
Convolutional neural networks are nowadays often used for classifying input data into specific possible classes for which the model was previously trained. Whatever test data we provide to the model, it will always predict the result corresponding class with specific certainty. The key problem with this approach is an inability of determining the data for which the model will most likely make a wrong prediction. Specifically because of that, it is a necessity to determine out-of-distribution data provided as input to the model, and the way to do that is by analyzing its output. Despite the fact that we cannot claim if the test data belongs to the distribution on which the model was trained or it is out-of-distribution, the possibility of detecting out-of-distribution data can be determined with various methods, including using AUROC and AUPR areas.
Keywords
Keywords (english)
Languagecroatian
URN:NBNurn:nbn:hr:168:925571
Study programmeTitle: Computing
Study programme type: university
Study level: undergraduate
Academic / professional title: sveučilišni/a prvostupnik/ prvostupnica (baccalaureus/baccalaurea) inženjer/inženjerka računarstva (sveučilišni/a prvostupnik/ prvostupnica (baccalaureus/baccalaurea) inženjer/inženjerka računarstva)
Type of resourceText
File originBorn digital
Access conditionsClosed access
Terms of useLicence In copyright icon
Public note
Created on2019-03-13 21:47:02