Image embeddings with Kolmogorov-Arnold networks
| dc.contributor.advisor | Кузьменко, Дмитро | uk_UA |
| dc.contributor.author | Юрченко, Артур | uk_UA |
| dc.date.accessioned | 2025-09-04T07:50:15Z | |
| dc.date.available | 2025-09-04T07:50:15Z | |
| dc.date.issued | 2025 | |
| dc.description.abstract | This research aims to evaluate performance of Kolmogorov-Arnold networks (KAN) in image embedding tasks. It focuses on modifying existing state-of-the-art architectures - CNN and ViT, replacing their MLP segments with KANs, aiming to improve their computational performance and embedding quality. Training and evaluation methodology is fully described in sections 4 and 5. | en_US |
| dc.identifier.uri | https://ekmair.ukma.edu.ua/handle/123456789/36430 | |
| dc.language.iso | en_US | en_US |
| dc.status | first published | en_US |
| dc.subject | Kolmogorov-Arnold networks | en_US |
| dc.subject | Computer Vision | en_US |
| dc.subject | Embedding | en_US |
| dc.subject | Convolutional neural networks | en_US |
| dc.subject | Vision Transformers | en_US |
| dc.subject | Encoders | en_US |
| dc.subject | Classification | en_US |
| dc.subject | Regression | en_US |
| dc.subject | Retrieval | en_US |
| dc.subject | Interpretability | en_US |
| dc.subject | bachelor`s thesis | en_US |
| dc.title | Image embeddings with Kolmogorov-Arnold networks | 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: