ScholarGate
Assistente

Comparar métodos

Examine os métodos selecionados lado a lado; as linhas que diferem ficam destacadas.

Máquina de Boltzmann Restrita (RBM)×Autoencoder×
ÁreaAprendizado profundoAprendizado profundo
FamíliaLatent structureMachine learning
Ano de origem19862006
Autor originalSmolensky, P. (1986); popularised by Hinton, G. E. & Salakhutdinov, R. R. (2006)Hinton, G.E. & Salakhutdinov, R.R.
TipoGenerative energy-based probabilistic modelNeural network (encoder-decoder)
Fonte seminalHinton, G. E., & Salakhutdinov, R. R. (2006). Reducing the Dimensionality of Data with Neural Networks. Science, 313(5786), 504–507. DOI ↗Hinton, G.E. & Salakhutdinov, R.R. (2006). Reducing the Dimensionality of Data with Neural Networks. Science, 313(5786), 504–507. DOI ↗
Outros nomesRBM, Harmonium, restricted Boltzmann machine, RBM generative modelOtokodlayıcı (Autoencoder), otokodlayıcı, auto-encoder, encoder-decoder network
Relacionados34
ResumoA Restricted Boltzmann Machine is a two-layer generative probabilistic model consisting of visible (observed) and hidden (latent) binary units connected by an undirected bipartite graph with no within-layer connections. Originally introduced as the 'Harmonium' by Paul Smolensky in 1986 and powerfully revived by Geoffrey Hinton and Ruslan Salakhutdinov in their landmark 2006 Science paper, RBMs became historically pivotal as the building block for greedy layer-wise pre-training of Deep Belief Networks, restarting interest in deep neural networks after years of stagnation.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.
ScholarGateConjunto de dados
  1. v1
  2. 4 Fontes
  3. PUBLISHED
  1. v1
  2. 1 Fontes
  3. PUBLISHED

Ir para a pesquisa Baixar slides

ScholarGateComparar métodos: Restricted Boltzmann Machine · Autoencoder. Recuperado em 2026-06-15 de https://scholargate.app/pt/compare