Institutional Repository of Vilnius University
Muzikos generavimas naudojant giliuosius neuroninius tinklus /
Abstract
dc:descriptionThe work is aimed at the suitability of the deep neural network for music generation. First of all, a literature review of deep neural networks and supervised machine learning was performed. Then training, validation and testing datasets were prepared. A long short-term memory neural network capable of generating music was developed and trained. Finally, evaluation metrics were used to evaluate the music generated by the network. The evaluation shows that the generated works tend to repeat the same notes, use most of the note classes and have more dominant note classes than the original pieces.
Degree
thesis:*- Grantor dc:publisher
- Institutional Repository of Vilnius University
- Year dc:date
- 2022
Author and committee
dc:creator, dc:contributor.*- Author dc:creator
-
- Talalas, Martynas,
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:ELABAETD146242477&prefLang=en_US