Porovnat metody
Prohlédněte si vybrané metody vedle sebe; řádky, které se liší, jsou zvýrazněny.
| Vision Transformer× | Stroj s podpůrnými vektory (klasifikace)× | |
|---|---|---|
| Obor≠ | Hluboké učení | Strojové učení |
| Rodina | Machine learning | Machine learning |
| Rok vzniku≠ | 2021 | 1995 |
| Tvůrce≠ | Dosovitskiy, A. et al. | Cortes, C. & Vapnik, V. |
| Typ≠ | Transformer architecture for images (self-attention over patches) | Maximum-margin classifier (kernel method) |
| Původní zdroj≠ | Dosovitskiy, A. et al. (2021). An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale. ICLR. link ↗ | Cortes, C. & Vapnik, V. (1995). Support-Vector Networks. Machine Learning, 20, 273–297. DOI ↗ |
| Další názvy | Görsel Transformer (ViT), görsel transformer, ViT, patch transformer for images | Destek Vektör Makinesi (SVM — Sınıflandırma), support-vector network, SVM classifier, maximum-margin classifier |
| Příbuzné | 5 | 5 |
| Shrnutí≠ | The Vision Transformer (ViT), introduced by Dosovitskiy and colleagues in 2021, splits an image into fixed-size patches, treats those patches as a sequence, and applies the Transformer self-attention mechanism to image classification. Given enough training data, it surpasses convolutional neural networks (CNNs). | The Support Vector Machine, introduced by Corinna Cortes and Vladimir Vapnik in 1995, is a classifier that finds the optimal separating hyperplane between classes in a high-dimensional space. It chooses the boundary that leaves the widest possible margin to the nearest training points, which makes its decisions robust on new data. |
| ScholarGateDatová sada ↗ |
|
|