Polunadzirano učenje s virtualnim neprijateljskim primjerima

master's thesis

• Title (english): Semi-supervised learning with virtual adversarial examples
• Author: Andrija Lonza
• Mentor: Siniša Šegvić (mentor)
• Committee member: Siniša Šegvić (predsjednik povjerenstva)
• Committee member: Stjepan Groš (član povjerenstva)
• Committee member: Vladimir Čeperić (član povjerenstva)
• Granter: University of Zagreb; Faculty of Electrical Engineering and Computing; Zagreb
• Defense date and country: 2020-07-15, Croatia
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Computing

Abstract

Diplomski rad obuhvaća kratku teoretsku razradu vrsta učenja modela u području dubokog učenja, te opsežnu teoretsku razradu metode polunadziranog učenja pod nazivom Polunadzirano učenje s virtualnim neprijateljskim primjerima. Predstavlja regularizacijsku tehniku učenja s virtualnim neprijateljskim primjerima koja potiče glatkoću decizijske granice zahtijevajući da neoznačeni primjeri imaju što sličniju predikciju kao i njihove perturbirane inačice. Predstavlja pojam virtualne neprijateljske perturbacije, te funkciju lokalne glatkoće razdiobe koje predstavljaju ključne pojmove u metodi. Provedeni su eksperimenti nad skupovima podataka MNIST, SVHN te CIFAR-10. Razvijen je postupak polunadziranog učenja klasifikacijskog modela zasnovan na virtualnim neprijateljskim primjerima.

Abstract (english)

The masters thesis includes a short theoretical elaboration of the types of model training in the field of deep learning and an extensive theoretical elaboration of the method of semi-supervised learning called Semi-supervised learning with virtual adversarial examples. It represents a regularization technique with virtual adversarial examples that encourages the smoothness of the decision boundary by requiring unlabeled examples to have as similar prediction as possible to their perturbed versions. It represents the term of virtual adversarial perturbation and the local smoothness distribution function that represent key terms in the method. Experiments were performed on the data sets MNIST, SVHN and CIFAR-10. A process of semi-supervised training of the classification model based on virtual adversarial examples has been developed.

• Keywords: virtualna; neprijateljska; perturbacija; VAT; regularizacija; lokalna glatkoća razdiobe; polunadzirana metoda
• Keywords (english): virtual; adversarial; perturbation; VAT; regularization; local smoothness of distribution; semi-supervised method
• Language: croatian
• URN:NBN: urn:nbn:hr:168:469407
• Study programme: Title: Computing; Study programme type: university; Study level: graduate; Academic / professional title: magistar/magistra inženjer/inženjerka računarstva (magistar/magistra inženjer/inženjerka računarstva)
• Type of resource: Text
• File origin: Born digital
• Access conditions: Closed access
• Created on: 2023-01-13 10:19:03