Comparer des méthodes

	Mécanisme d'attention	Auto-attention multi-têtes	Modèle séquence-à-séquence (Seq2Seq)
Domaine	Apprentissage profond	Apprentissage profond	Apprentissage profond
Famille	Machine learning	Machine learning	Machine learning
Année d'origine	2015	2017	2014
Auteur d'origine	Bahdanau, D.; Luong, M.T.	Vaswani, A. et al.	Sutskever, I.; Cho, K.
Type	Neural attention layer (encoder-decoder)	Attention mechanism (Transformer core)	Encoder-decoder neural network (deep learning)
Source fondatrice	Bahdanau, D., Cho, K. & Bengio, Y. (2015). Neural Machine Translation by Jointly Learning to Align and Translate. ICLR.	Vaswani, A. et al. (2017). Attention Is All You Need. NeurIPS.	Sutskever, I., Vinyals, O. & Le, Q. V. (2014). Sequence to Sequence Learning with Neural Networks. NeurIPS.
Alias	Dikkat Mekanizması (Bahdanau / Luong Attention), dikkat mekanizmasi, neural attention, additive attention	Öz-Dikkat ve Çok Başlı Dikkat (Multi-Head Self-Attention), öz-dikkat, multi-head attention, scaled dot-product attention	Dizi-Dizi Modeli (Seq2Seq — Encoder-Decoder), encoder-decoder model, seq2seq, sequence to sequence learning
Apparentées	5	5	5
Résumé	The attention mechanism, introduced by Bahdanau, Cho and Bengio in 2015 and refined by Luong, Pham and Manning the same year, lets a sequence decoder dynamically learn which of the encoder's outputs to focus on at each step. Before the Transformer, it substantially improved machine-translation quality by freeing models from compressing an entire input into a single fixed vector.	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.	The sequence-to-sequence (Seq2Seq) model, introduced by Sutskever, Vinyals and Le and by Cho and colleagues in 2014, is an encoder-decoder neural network that maps a variable-length input sequence to a variable-length output sequence. It is the foundation of machine translation, text summarization, dialogue systems and code generation.