Methoden vergleichen
Prüfen Sie die ausgewählten Methoden nebeneinander; abweichende Zeilen sind hervorgehoben.
| Vision Transformer× | Generative Adversarial Network× | Support Vector Machine (Klassifikation)× | |
|---|---|---|---|
| Fachgebiet≠ | Deep Learning | Deep Learning | Maschinelles Lernen |
| Familie | Machine learning | Machine learning | Machine learning |
| Entstehungsjahr≠ | 2021 | 2014 | 1995 |
| Urheber≠ | Dosovitskiy, A. et al. | Goodfellow, I. et al. | Cortes, C. & Vapnik, V. |
| Typ≠ | Transformer architecture for images (self-attention over patches) | Generative deep learning (adversarial two-network game) | Maximum-margin classifier (kernel method) |
| Wegweisende Quelle≠ | Dosovitskiy, A. et al. (2021). An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale. ICLR. link ↗ | Goodfellow, I. et al. (2014). Generative Adversarial Nets. NeurIPS. link ↗ | Cortes, C. & Vapnik, V. (1995). Support-Vector Networks. Machine Learning, 20, 273–297. DOI ↗ |
| Aliasnamen | Görsel Transformer (ViT), görsel transformer, ViT, patch transformer for images | Üretici Çekişmeli Ağ (GAN), GAN, generative adversarial nets, adversarial network | Destek Vektör Makinesi (SVM — Sınıflandırma), support-vector network, SVM classifier, maximum-margin classifier |
| Verwandt≠ | 5 | 4 | 5 |
| Zusammenfassung≠ | 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). | A Generative Adversarial Network (GAN), introduced by Ian Goodfellow and colleagues in 2014, produces realistic synthetic data through the competition of two neural networks — a generator and a discriminator. It is widely used for image synthesis, data augmentation, and distribution estimation. | 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. |
| ScholarGateDatensatz ↗ |
|
|
|