ScholarGate
Asistent
Machine learning

Autoenkoder

Autoenkoder je neuronska mreža tipa enkoder-dekoder, koju su popularizovali Hinton i Salakhutdinov 2006. godine, a koja komprimuje podatke u niskodimenzionalni latentni kod, a zatim ih rekonstruiše, omogućavajući redukciju dimenzionalnosti i detekciju anomalija. Učeći da obnovi sopstveni ulaz kroz usko grlo, otkriva kompaktnu reprezentaciju podataka.

Otvorite u MethodMindUskoroVideoUskoroDownload slides

Pročitajte celu metodu

Samo za članove

Prijavite se besplatnim nalogom da biste pročitali ovaj odeljak.

Prijavite se

Method map

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

+4 more

Izvori

  1. Hinton, G.E. & Salakhutdinov, R.R. (2006). Reducing the Dimensionality of Data with Neural Networks. Science, 313(5786), 504–507. DOI: 10.1126/science.1127647

Kako citirati ovu stranicu

ScholarGate. (2026, June 1). Autoencoder (Encoder-Decoder Neural Network for Dimensionality Reduction). ScholarGate. https://scholargate.app/sr/deep-learning/autoencoder

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

ScholarGateAutoencoder (Autoencoder (Encoder-Decoder Neural Network for Dimensionality Reduction)). Preuzeto 2026-06-15 sa https://scholargate.app/sr/deep-learning/autoencoder · Skup podataka: https://doi.org/10.5281/zenodo.20539026