Image embeddings with Kolmogorov-Arnold networks

dc.contributor.advisorКузьменко, Дмитроuk_UA
dc.contributor.authorЮрченко, Артурuk_UA
dc.date.accessioned2025-09-04T07:50:15Z
dc.date.available2025-09-04T07:50:15Z
dc.date.issued2025
dc.description.abstractThis 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.urihttps://ekmair.ukma.edu.ua/handle/123456789/36430
dc.language.isoen_USen_US
dc.statusfirst publisheden_US
dc.subjectKolmogorov-Arnold networksen_US
dc.subjectComputer Visionen_US
dc.subjectEmbeddingen_US
dc.subjectConvolutional neural networksen_US
dc.subjectVision Transformersen_US
dc.subjectEncodersen_US
dc.subjectClassificationen_US
dc.subjectRegressionen_US
dc.subjectRetrievalen_US
dc.subjectInterpretabilityen_US
dc.subjectbachelor`s thesisen_US
dc.titleImage embeddings with Kolmogorov-Arnold networksen_US
dc.typeOtheren_US
Files
Original bundle
Now showing 1 - 2 of 2
Loading...
Thumbnail Image
Name:
Yurchenko_Bakalavrska_robota.pdf
Size:
298.4 KB
Format:
Adobe Portable Document Format
Loading...
Thumbnail Image
Name:
Yurchenko_Bakalavrska_robota_1.pdf
Size:
338.81 KB
Format:
Adobe Portable Document Format
License bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
1.71 KB
Format:
Item-specific license agreed upon to submission
Description: