Back to search

Institutional Repository of Vilnius University

Investigation of generalization properties of convolutional neural networks /

Abstract

dc:description

In this master’s thesis the analysis of the current state of generalization properties on convolutional neural networks was done, investigated the impact of plain convolutional neural network architecture (ResNet and DenseNet with different number of layers) on convolutional neural network training and generalization and compared with ensembled network models. Investigated the impact of data augmentation on image level (CIFAR-10 and CIFAR-100 datasets), implemented data augmentation on non-image level and tested what impact it has to generalization compared with image level results. Conducted experiments allowed us to draw a conclusion that: data augmentation on non-image level brings better generalization compared to traditional data augmentation on image level. Both ensembled network models (ResNet and DenseNet) showed better results on generalization compared with plain convolutional neural network architectures, because individually each convolutional neural network has its own weaknesses, but together when they aggregated to generate single output – they are showing slightly better generalization results.

Degree

thesis:*
Grantor dc:publisher
Institutional Repository of Vilnius University
Year dc:date
2023

Author and committee

dc:creator, dc:contributor.*
Author dc:creator
  • Ščigla, Edvinas,

Subjects

dc:subject × 1

Rights

dc:rights
Statement dc:rights
  • info:eu-repo/semantics/openAccess
Language dc:language
eng

Identifiers

dc:identifier.*

Chain of custody

source
Harvested from
Vilnius University
Base URL
epublications.vu.lt/oai
Last updated
2026-11-19
Source record
OAI-PMH GetRecord
citation

Ščigla, Edvinas,. Investigation of generalization properties of convolutional neural networks /. Institutional Repository of Vilnius University, 2023. https://repository.vu.lt/VU:ELABAETD192827908&prefLang=en_US