Compara mètodes

	Unitat recurrent amb portes (GRU)	Mecanisme d'atenció	RNN bidireccional
Camp	Aprenentatge profund	Aprenentatge profund	Aprenentatge profund
Família	Machine learning	Machine learning	Machine learning
Any d'origen	2014	2015	1997
Autor original	Cho, K. et al.	Bahdanau, D.; Luong, M.T.	Schuster, M. & Paliwal, K.K.
Tipus	Gated recurrent neural network unit	Neural attention layer (encoder-decoder)	Recurrent neural network (sequence model)
Font seminal	Cho, K. et al. (2014). Learning Phrase Representations using RNN Encoder–Decoder for Statistical Machine Translation. EMNLP.	Bahdanau, D., Cho, K. & Bengio, Y. (2015). Neural Machine Translation by Jointly Learning to Align and Translate. ICLR.	Schuster, M. & Paliwal, K.K. (1997). Bidirectional Recurrent Neural Networks. IEEE Transactions on Signal Processing, 45(11), 2673–2681.
Àlies	Kapılı Tekrarlayan Birim (GRU), gated recurrent unit, gated recurrent network	Dikkat Mekanizması (Bahdanau / Luong Attention), dikkat mekanizmasi, neural attention, additive attention	Çift Yönlü RNN / BiLSTM / BiGRU, bidirectional recurrent neural network, BiLSTM, BiGRU
Relacionats	5	5	5
Resum	The Gated Recurrent Unit (GRU) is a gated recurrent neural network cell introduced by Cho and colleagues in 2014 that captures long-range dependencies in sequential data using update and reset gates, achieving performance comparable to LSTM with fewer parameters.	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.	A Bidirectional RNN, introduced by Schuster and Paliwal in 1997, processes a sequence in both forward and backward directions so that every position has access to its full surrounding context. With LSTM or GRU cells (BiLSTM/BiGRU) it is the standard approach for named-entity recognition, sequence labelling, and speech recognition.