Comparer des méthodes

	Auto-attention multi-têtes	Forêt Aléatoire
Domaine	Apprentissage profond	Apprentissage automatique
Famille	Machine learning	Machine learning
Année d'origine	2017	2001
Auteur d'origine	Vaswani, A. et al.	Breiman, L.
Type	Attention mechanism (Transformer core)	Ensemble (bagging of decision trees)
Source fondatrice	Vaswani, A. et al. (2017). Attention Is All You Need. NeurIPS.	Breiman, L. (2001). Random Forests. Machine Learning, 45, 5–32.
Alias	Öz-Dikkat ve Çok Başlı Dikkat (Multi-Head Self-Attention), öz-dikkat, multi-head attention, scaled dot-product attention	Rastgele Orman (Random Forest), rastgele orman, random decision forest, bagged tree ensemble
Apparentées	5	4
Résumé	Multi-head self-attention, introduced by Vaswani and colleagues in 2017, is the mechanism that lets every position in a sequence compute its relationship to all other positions in parallel. It is the core of the Transformer architecture and the foundation underneath BERT, GPT, and T5.	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.