Porovnat metody
Prohlédněte si vybrané metody vedle sebe; řádky, které se liší, jsou zvýrazněny.
| Gated Recurrent Unit (GRU)× | Mechanismus pozornosti× | |
|---|---|---|
| Obor | Hluboké učení | Hluboké učení |
| Rodina | Machine learning | Machine learning |
| Rok vzniku≠ | 2014 | 2015 |
| Tvůrce≠ | Cho, K. et al. | Bahdanau, D.; Luong, M.T. |
| Typ≠ | Gated recurrent neural network unit | Neural attention layer (encoder-decoder) |
| Původní zdroj≠ | Cho, K. et al. (2014). Learning Phrase Representations using RNN Encoder–Decoder for Statistical Machine Translation. EMNLP. link ↗ | Bahdanau, D., Cho, K. & Bengio, Y. (2015). Neural Machine Translation by Jointly Learning to Align and Translate. ICLR. link ↗ |
| Další názvy≠ | Kapılı Tekrarlayan Birim (GRU), gated recurrent unit, gated recurrent network | Dikkat Mekanizması (Bahdanau / Luong Attention), dikkat mekanizmasi, neural attention, additive attention |
| Příbuzné | 5 | 5 |
| Shrnutí≠ | 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. |
| ScholarGateDatová sada ↗ |
|
|