Institutional Repository of Vilnius University
Mokymosi neuroniniuose tinkluose optimizavimas /
Abstract
dc:descriptionLooking for ways how to improve and optimise single-layer artificial neural network learning in solving the classification task. Tasks of classification type often occur in practice - medicine, army, security systems and other areas. Most often, artificial neural networks using machine learning are used to solve the classification task. Occasionally, incorrect or too slow grading can cause catastrophic consequences, so finding ways to optimize the learning of artificial neural networks is very important. The paper examines two ways to optimize training. One of the way, is to try use different desired output values in machine learning. This method is effective when the classified data sets intersect or have similar parameters. Another research method is using an artificial neural network which is already trained with other similar in some ways data.
Degree
thesis:*- Grantor dc:publisher
- Institutional Repository of Vilnius University
- Year dc:date
- 2019
Author and committee
dc:creator, dc:contributor.*- Author dc:creator
-
- Kvedaravičius, Aidas,
- Contributors dc:contributor
-
- Radavičius, Irmantas
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:ELABAETD81918843&prefLang=en_US