Порівняння методів

	Модель послідовність-послідовність	Механізм уваги	Багатоголова самостійна увага
Галузь	Глибоке навчання	Глибоке навчання	Глибоке навчання
Родина	Machine learning	Machine learning	Machine learning
Рік появи	2014	2015	2017
Автор методу	Sutskever, I.; Cho, K.	Bahdanau, D.; Luong, M.T.	Vaswani, A. et al.
Тип	Encoder-decoder neural network (deep learning)	Neural attention layer (encoder-decoder)	Attention mechanism (Transformer core)
Основоположне джерело	Sutskever, I., Vinyals, O. & Le, Q. V. (2014). Sequence to Sequence Learning with Neural Networks. NeurIPS.	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.
Інші назви	Dizi-Dizi Modeli (Seq2Seq — Encoder-Decoder), encoder-decoder model, seq2seq, sequence to sequence learning	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
Пов'язані	5	5	5
Підсумок	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.	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.