Módszerek összehasonlítása
Tekintse át a kiválasztott módszereket egymás mellett; az eltérő sorok kiemelve jelennek meg.
| Long Short-Term Memory (LSTM)× | Gated Recurrent Unit (GRU)× | |
|---|---|---|
| Tudományterület | Mélytanulás | Mélytanulás |
| Módszercsalád | Machine learning | Machine learning |
| Keletkezés éve≠ | 1997 | 2014 |
| Megalkotó≠ | Hochreiter, S. & Schmidhuber, J. | Cho, K., van Merrienboer, B., Gulcehre, C., Bahdanau, D., Bougares, F., Schwenk, H., & Bengio, Y. |
| Típus≠ | Recurrent neural network with gated memory cells | Recurrent neural network with gating |
| Alapmű≠ | Hochreiter, S. & Schmidhuber, J. (1997). Long short-term memory. Neural Computation, 9(8), 1735–1780. DOI ↗ | Cho, K., van Merrienboer, B., Gulcehre, C., Bahdanau, D., Bougares, F., Schwenk, H., & Bengio, Y. (2014). Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation. In Proceedings of EMNLP 2014, pp. 1724–1734. link ↗ |
| Alternatív nevek | LSTM, LSTM network, LSTM-RNN, long short-term memory RNN | GRU, GRU network, gated RNN, GRU cell |
| Kapcsolódó≠ | 4 | 3 |
| Összefoglaló≠ | Long Short-Term Memory (LSTM) is a gated recurrent neural network architecture introduced by Hochreiter and Schmidhuber in 1997. It was designed to learn dependencies across long sequences by using dedicated memory cells and three learned gates — forget, input, and output — that control what information is retained, updated, or passed forward at each time step. | The Gated Recurrent Unit (GRU), introduced by Cho et al. in 2014, is a streamlined recurrent neural network that uses two learned gates — an update gate and a reset gate — to selectively retain or discard information across time steps, enabling effective sequence modelling with fewer parameters than LSTM. |
| ScholarGateAdatkészlet ↗ |
|
|