Institutional Repository of Vilnius University
Nuotraukų klasifikavimas naudojant mašininį mokymąsi bei dimensijų mažinimo metodus /
Abstract
dc:descriptionMachine learning model training time can be significantly reduced by using dimensionality reduction techniques. This paper investigates principal component analysis, linear discriminant analysis and latent semantic analysis techniques’ impact on machine learning model’s accuracy and training time. In this paper, literature analysis, evaluation metrics, data augmentation, grid search for the best hyperparameters are carried out. Dimensionality reduction techniques proved to achieve significantly shorter training time with little accuracy lost.
Degree
thesis:*- Grantor dc:publisher
- Institutional Repository of Vilnius University
- Year dc:date
- 2021
Author and committee
dc:creator, dc:contributor.*- Author dc:creator
-
- Kondratavičius, Justas,
- Contributors dc:contributor
-
- Ragaišis, Jonas
Rights
dc:rights- Statement dc:rights
-
- info:eu-repo/semantics/openAccess
- Language dc:language
- lit
Identifiers
dc:identifier.*- Repository record dc:identifier
- https://repository.vu.lt/VU:ELABAETD107116064&prefLang=en_US