Usporedite metode
Pregledajte odabrane metode jednu uz drugu; retci koji se razlikuju su istaknuti.
| Autoenkoder× | Višeslojni perceptron (MLP)× | |
|---|---|---|
| Područje | Duboko učenje | Duboko učenje |
| Obitelj | Machine learning | Machine learning |
| Godina nastanka≠ | 2006 | 1986 |
| Tvorac≠ | Hinton, G.E. & Salakhutdinov, R.R. | Rumelhart, D. E.; Hinton, G. E.; Williams, R. J. |
| Vrsta≠ | Neural network (encoder-decoder) | Supervised feedforward neural network |
| Temeljni izvor≠ | Hinton, G.E. & Salakhutdinov, R.R. (2006). Reducing the Dimensionality of Data with Neural Networks. Science, 313(5786), 504–507. DOI ↗ | Rumelhart, D. E., Hinton, G. E. & Williams, R. J. (1986). Learning representations by back-propagating errors. Nature, 323, 533–536. DOI ↗ |
| Drugi nazivi≠ | Otokodlayıcı (Autoencoder), otokodlayıcı, auto-encoder, encoder-decoder network | MLP, feedforward neural network, fully connected neural network, vanilla neural network |
| Srodne | 4 | 4 |
| Sažetak≠ | 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 Multilayer Perceptron is a classic fully connected feedforward neural network trained with the backpropagation algorithm, as formalised by Rumelhart, Hinton & Williams in their landmark 1986 Nature paper. Composed of an input layer, one or more hidden layers of neurons, and an output layer, the MLP learns nonlinear mappings from input features to target outputs and serves as the foundational building block of modern deep learning. |
| ScholarGateSkup podataka ↗ |
|
|