ScholarGate
Asystent

Porównaj metody

Przeglądaj wybrane metody obok siebie; wiersze, które się różnią, są wyróżnione.

Głęboka Sieć Przekonań (DBN)×Autoenkoder×
DziedzinaUczenie głębokieUczenie głębokie
RodzinaMachine learningMachine learning
Rok powstania20062006
TwórcaGeoffrey Hinton, Simon Osindero & Yee-Whye TehHinton, G.E. & Salakhutdinov, R.R.
TypGenerative probabilistic modelNeural network (encoder-decoder)
Źródło pierwotneHinton, G. E., Osindero, S., & Teh, Y.-W. (2006). A fast learning algorithm for deep belief nets. Neural Computation, 18(7), 1527–1554. DOI ↗Hinton, G.E. & Salakhutdinov, R.R. (2006). Reducing the Dimensionality of Data with Neural Networks. Science, 313(5786), 504–507. DOI ↗
Inne nazwyDBN, Deep Generative Network, Stacked RBM Network, Derin İnanç AğıOtokodlayıcı (Autoencoder), otokodlayıcı, auto-encoder, encoder-decoder network
Pokrewne34
PodsumowanieA Deep Belief Network is a generative probabilistic model composed of multiple layers of stochastic, latent variables. Introduced by Hinton, Osindero, and Teh in 2006, DBNs were among the first deep architectures to be trained efficiently. Each pair of adjacent layers forms a Restricted Boltzmann Machine, and the network is trained greedily, one layer at a time, before optional supervised fine-tuning. DBNs revived interest in deep learning and demonstrated that hierarchical feature learning from raw data is tractable.An autoencoder is an encoder-decoder neural network, popularised by Hinton and Salakhutdinov in 2006, that compresses data into a low-dimensional latent code and then reconstructs it, enabling dimensionality reduction and anomaly detection. By learning to rebuild its own input through a narrow bottleneck, it discovers a compact representation of the data.
ScholarGateZbiór danych
  1. v1
  2. 1 Źródła
  3. PUBLISHED
  1. v1
  2. 1 Źródła
  3. PUBLISHED

Przejdź do wyszukiwania Pobierz slajdy

ScholarGatePorównaj metody: Deep Belief Network · Autoencoder. Pobrano 2026-06-15 z https://scholargate.app/pl/compare