ScholarGate
Asistent
Machine learning

Gated Recurrent Unit (GRU)

Gated Recurrent Unit (GRU) je ćelijski tip rekurirajuće neuronske mreže s kapijama, koji su 2014. godine predstavili Cho i saradnici. On hvata dugoročne zavisnosti u sekvencijalnim podacima pomoću ulaznih i resetirajućih kapija, postižući performanse usporedive s LSTM mrežama, ali s manjim brojem parametara.

Otvorite u MethodMindUskoroVideoUskoroDownload slides

Pročitajte cijelu metodu

Samo za članove

Prijavite se besplatnim računom kako biste pročitali ovaj odjeljak.

Prijavite se

Method map

The neighbourhood of related methods — select a node to explore.

Izvori

  1. Cho, K. et al. (2014). Learning Phrase Representations using RNN Encoder–Decoder for Statistical Machine Translation. EMNLP. link
  2. Chung, J., Gulcehre, C., Cho, K. & Bengio, Y. (2014). Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling. NIPS 2014 Deep Learning Workshop. arXiv:1412.3555 link

Kako citirati ovu stranicu

ScholarGate. (2026, June 1). Gated Recurrent Unit. ScholarGate. https://scholargate.app/hr/deep-learning/gru

Which method?

Set this method beside its closest kin and read them side by side — the library lays the books on the table; the choice is yours.

Compare side by side

Citirana u

ScholarGateGRU (Gated Recurrent Unit). Preuzeto 2026-06-15 s https://scholargate.app/hr/deep-learning/gru · Skup podataka: https://doi.org/10.5281/zenodo.20539026