Vertaile menetelmiä
Tarkastele valitsemiasi menetelmiä rinnakkain; eroavat rivit korostetaan.
| Autoenkooderi× | Isomap× | |
|---|---|---|
| Tieteenala≠ | Syväoppiminen | Koneoppiminen |
| Menetelmäperhe≠ | Machine learning | Latent structure |
| Syntyvuosi≠ | 2006 | 2000 |
| Kehittäjä≠ | Hinton, G.E. & Salakhutdinov, R.R. | Tenenbaum, J. B.; de Silva, V.; Langford, J. C. |
| Tyyppi≠ | Neural network (encoder-decoder) | Manifold learning / nonlinear dimensionality reduction |
| Alkuperäislähde≠ | Hinton, G.E. & Salakhutdinov, R.R. (2006). Reducing the Dimensionality of Data with Neural Networks. Science, 313(5786), 504–507. DOI ↗ | Tenenbaum, J. B., de Silva, V. & Langford, J. C. (2000). A global geometric framework for nonlinear dimensionality reduction. Science, 290(5500), 2319–2323. DOI ↗ |
| Rinnakkaisnimet | Otokodlayıcı (Autoencoder), otokodlayıcı, auto-encoder, encoder-decoder network | Isomap, isometric feature mapping, geodesic Isomap, nonlinear MDS |
| Liittyvät≠ | 4 | 3 |
| Tiivistelmä≠ | 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. | Isomap (Isometric Feature Mapping) is a manifold learning algorithm introduced by Tenenbaum, de Silva, and Langford in 2000 that discovers the intrinsic low-dimensional geometry of high-dimensional data by preserving geodesic — rather than straight-line Euclidean — distances between all pairs of points. It was one of the earliest, and most influential, nonlinear dimensionality reduction methods to demonstrate that genuinely curved data manifolds could be unfolded into a faithful low-dimensional coordinate system. |
| ScholarGateAineisto ↗ |
|
|