Hybrid Random Fields
| dc.contributor.advisor | Chornei, Ruslan | |
| dc.contributor.author | Zhydok, Fedir | |
| dc.date.accessioned | 2024-11-06T10:06:49Z | |
| dc.date.available | 2024-11-06T10:06:49Z | |
| dc.date.issued | 2024 | |
| dc.description.abstract | In this thesis, the capabilities of developed realization of Hybrid Random Fields is explored in terms of classification and regression tasks. The graphical model is compared to classical machine learning approaches in these tasks in terms of time and model quality. Furthermore, different structure learning approaches for Hybrid Random Fields are compared too in order to establish whether time-efficient K2 approach produces structures as well as hill-climbing algorithm with exhaustive search. | en_US |
| dc.identifier.uri | https://ekmair.ukma.edu.ua/handle/123456789/32221 | |
| dc.language.iso | en | en_US |
| dc.subject | graphical probabilistic models | en_US |
| dc.subject | machine learning | en_US |
| dc.subject | Bayesian Networks | en_US |
| dc.subject | Hybrid Random Fields | en_US |
| dc.subject | bachelor thesis | en_US |
| dc.title | Hybrid Random Fields | en_US |
| dc.type | Other | en_US |
Files
License bundle
1 - 1 of 1
No Thumbnail Available
- Name:
- license.txt
- Size:
- 1.71 KB
- Format:
- Item-specific license agreed upon to submission
- Description: