Porównaj metody
Przeglądaj wybrane metody obok siebie; wiersze, które się różnią, są wyróżnione.
| Autoenkoder× | Głęboka Sieć Przekonań (DBN)× | |
|---|---|---|
| Dziedzina | Uczenie głębokie | Uczenie głębokie |
| Rodzina | Machine learning | Machine learning |
| Rok powstania | 2006 | 2006 |
| Twórca≠ | Hinton, G.E. & Salakhutdinov, R.R. | Geoffrey Hinton, Simon Osindero & Yee-Whye Teh |
| Typ≠ | Neural network (encoder-decoder) | Generative probabilistic model |
| Źródło pierwotne≠ | Hinton, G.E. & Salakhutdinov, R.R. (2006). Reducing the Dimensionality of Data with Neural Networks. Science, 313(5786), 504–507. DOI ↗ | Hinton, G. E., Osindero, S., & Teh, Y.-W. (2006). A fast learning algorithm for deep belief nets. Neural Computation, 18(7), 1527–1554. DOI ↗ |
| Inne nazwy | Otokodlayıcı (Autoencoder), otokodlayıcı, auto-encoder, encoder-decoder network | DBN, Deep Generative Network, Stacked RBM Network, Derin İnanç Ağı |
| Pokrewne≠ | 4 | 3 |
| Podsumowanie≠ | 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. | A 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. |
| ScholarGateZbiór danych ↗ |
|
|