ScholarGate
Asistente

Comparar métodos

Revisa los métodos seleccionados uno junto a otro; las filas que difieren aparecen resaltadas.

Mecanismo de atención×LSTM×
CampoAprendizaje profundoAprendizaje profundo
FamiliaMachine learningMachine learning
Año de origen20151997
Autor originalBahdanau, D.; Luong, M.T.Hochreiter, S. & Schmidhuber, J.
TipoNeural attention layer (encoder-decoder)Recurrent neural network (gated memory cell)
Fuente seminalBahdanau, D., Cho, K. & Bengio, Y. (2015). Neural Machine Translation by Jointly Learning to Align and Translate. ICLR. link ↗Hochreiter, S. & Schmidhuber, J. (1997). Long Short-Term Memory. Neural Computation, 9(8), 1735–1780. DOI ↗
AliasDikkat Mekanizması (Bahdanau / Luong Attention), dikkat mekanizmasi, neural attention, additive attentionLSTM (Uzun Kısa Dönem Bellek Ağı), long short-term memory, LSTM network, recurrent neural network with memory cells
Relacionados55
ResumenThe 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.LSTM (Long Short-Term Memory) is a recurrent neural network architecture, introduced by Sepp Hochreiter and Jürgen Schmidhuber in 1997, that can learn long-term dependencies in sequential data and is widely used for time-series and sequence prediction. It keeps an internal memory that lets information persist across many time steps.
ScholarGateConjunto de datos
  1. v1
  2. 2 Fuentes
  3. PUBLISHED
  1. v1
  2. 1 Fuentes
  3. PUBLISHED

Ir a la búsqueda Descargar diapositivas

ScholarGateComparar métodos: Attention Mechanism · LSTM. Recuperado el 2026-06-20 de https://scholargate.app/es/compare