Usporedite metode
Pregledajte odabrane metode jednu uz drugu; retci koji se razlikuju su istaknuti.
| Rekurentna neuronska mreža× | Gated Recurrent Unit (GRU)× | |
|---|---|---|
| Područje | Duboko učenje | Duboko učenje |
| Obitelj | Machine learning | Machine learning |
| Godina nastanka≠ | 1986–1990 | 2014 |
| Tvorac≠ | Rumelhart, D. E.; Elman, J. L. | Cho, K., van Merrienboer, B., Gulcehre, C., Bahdanau, D., Bougares, F., Schwenk, H., & Bengio, Y. |
| Vrsta≠ | Sequential neural network | Recurrent neural network with gating |
| Temeljni izvor≠ | Elman, J. L. (1990). Finding structure in time. Cognitive Science, 14(2), 179–211. 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 ↗ |
| Drugi nazivi | RNN, Elman network, Jordan network, simple recurrent network | GRU, GRU network, gated RNN, GRU cell |
| Srodne | 3 | 3 |
| Sažetak≠ | A Recurrent Neural Network (RNN) is a class of neural network designed to process sequential data by maintaining a hidden state that carries information across time steps. Introduced in its modern form by Rumelhart et al. (1986) and further shaped by Elman (1990), RNNs became the dominant architecture for sequence modelling in NLP, speech, and time-series analysis before the rise of attention-based models. | 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. |
| ScholarGateSkup podataka ↗ |
|
|