ScholarGate
Avustaja

Vertaile menetelmiä

Tarkastele valitsemiasi menetelmiä rinnakkain; eroavat rivit korostetaan.

Huomiomekanismi×Kaksisuuntainen RNN×
TieteenalaSyväoppiminenSyväoppiminen
MenetelmäperheMachine learningMachine learning
Syntyvuosi20151997
KehittäjäBahdanau, D.; Luong, M.T.Schuster, M. & Paliwal, K.K.
TyyppiNeural attention layer (encoder-decoder)Recurrent neural network (sequence model)
AlkuperäislähdeBahdanau, D., Cho, K. & Bengio, Y. (2015). Neural Machine Translation by Jointly Learning to Align and Translate. ICLR. link ↗Schuster, M. & Paliwal, K.K. (1997). Bidirectional Recurrent Neural Networks. IEEE Transactions on Signal Processing, 45(11), 2673–2681. DOI ↗
RinnakkaisnimetDikkat Mekanizması (Bahdanau / Luong Attention), dikkat mekanizmasi, neural attention, additive attentionÇift Yönlü RNN / BiLSTM / BiGRU, bidirectional recurrent neural network, BiLSTM, BiGRU
Liittyvät55
TiivistelmäThe 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.
ScholarGateAineisto
  1. v1
  2. 2 Lähteet
  3. PUBLISHED
  1. v1
  2. 2 Lähteet
  3. PUBLISHED

Siirry hakuun Lataa diat

ScholarGateVertaile menetelmiä: Attention Mechanism · Bidirectional RNN. Haettu 2026-06-19 osoitteesta https://scholargate.app/fi/compare