Back to search
Institutional Repository of Vilnius University
Laiko eilučių modelių modeliavimas panaudojant natūralios kalbos modelius /
Abstract
dc:descriptionThis thesis researches relationship between cryptocurrency time series data and Twitter’s tweets about them. By converting time series into images, the original CLIP model is trained to understand new relationships. Then a modified CLIP model is proposed that accepts time series directly without the need for any conversion.
Degree
thesis:*- Grantor dc:publisher
- Institutional Repository of Vilnius University
- Year dc:date
- 2023
Author and committee
dc:creator, dc:contributor.*- Author dc:creator
-
- Gaulia, Matas,
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:ELABAETD192844732&prefLang=en_US