Institutional Repository of Vilnius University
Nesubalansuotų duomenų problemos sprendimas taikant giliuosius neuroninius tinklus /
Abstract
dc:descriptionThe paper examines three solution methods - sample removal (undersampling), sample generation (oversampling), and a combination of the two. The experiment uses object segmentation and object detection tasks. A large-scale BDD100K driving dataset is used. The aim of this paper is to investigate the problem of unbalanced datasets for machine learning, its solutions and the effectiveness of the solutions, and to perform experiments on a selected unbalanced dataset. The expected results of the project are to identify the most efficient way to solve the problem of unbalanced datasets, to present the results obtained and to draw conclusions from the analysis.
Degree
thesis:*- Grantor dc:publisher
- Institutional Repository of Vilnius University
- Year dc:date
- 2022
Author and committee
dc:creator, dc:contributor.*- Author dc:creator
-
- Valvonis, Dautartas,
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:ELABAETD146242987&prefLang=en_US