השוואת שיטות

	טרנספורמר ראייה	רשת יריבות יוצרת (Generative Adversarial Network)	מכונת וקטורים תומכים (סיווג)
תחום	למידה עמוקה	למידה עמוקה	למידת מכונה
משפחה	Machine learning	Machine learning	Machine learning
שנת המקור	2021	2014	1995
הוגה השיטה	Dosovitskiy, A. et al.	Goodfellow, I. et al.	Cortes, C. & Vapnik, V.
סוג	Transformer architecture for images (self-attention over patches)	Generative deep learning (adversarial two-network game)	Maximum-margin classifier (kernel method)
מקור מכונן	Dosovitskiy, A. et al. (2021). An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale. ICLR.	Goodfellow, I. et al. (2014). Generative Adversarial Nets. NeurIPS.	Cortes, C. & Vapnik, V. (1995). Support-Vector Networks. Machine Learning, 20, 273–297.
כינויים	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
קשורות	5	4	5
תקציר	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.