Порівняння методів

	Трансформер для комп'ютерного зору	Випадковий ліс	Метод опорних векторів (класифікація)
Галузь	Глибоке навчання	Машинне навчання	Машинне навчання
Родина	Machine learning	Machine learning	Machine learning
Рік появи	2021	2001	1995
Автор методу	Dosovitskiy, A. et al.	Breiman, L.	Cortes, C. & Vapnik, V.
Тип	Transformer architecture for images (self-attention over patches)	Ensemble (bagging of decision trees)	Maximum-margin classifier (kernel method)
Основоположне джерело	Dosovitskiy, A. et al. (2021). An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale. ICLR.	Breiman, L. (2001). Random Forests. Machine Learning, 45, 5–32.	Cortes, C. & Vapnik, V. (1995). Support-Vector Networks. Machine Learning, 20, 273–297.
Інші назви	Görsel Transformer (ViT), görsel transformer, ViT, patch transformer for images	Rastgele Orman (Random Forest), rastgele orman, random decision forest, bagged tree ensemble	Destek Vektör Makinesi (SVM — Sınıflandırma), support-vector network, SVM classifier, maximum-margin classifier
Пов'язані	5	4	5
Підсумок	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).	Random Forest is an ensemble learning method, introduced by Leo Breiman in 2001, that grows many decision trees on bootstrap samples of the data and combines their votes to produce strong classification and regression. By pooling many slightly different trees, it produces more accurate and more stable predictions than any single tree.	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.