Methoden vergelijken
Bekijk de geselecteerde methoden naast elkaar; rijen die verschillen zijn gemarkeerd.
| Auto-encoder× | Convolutional Neural Network (Classificatie)× | Random Forest× | |
|---|---|---|---|
| Vakgebied≠ | Deep learning | Deep learning | Machine learning |
| Familie | Machine learning | Machine learning | Machine learning |
| Jaar van ontstaan≠ | 2006 | 1998 | 2001 |
| Grondlegger≠ | Hinton, G.E. & Salakhutdinov, R.R. | LeCun, Y. et al. | Breiman, L. |
| Type≠ | Neural network (encoder-decoder) | Deep neural network (convolutional) | Ensemble (bagging of decision trees) |
| Oorspronkelijke bron≠ | Hinton, G.E. & Salakhutdinov, R.R. (2006). Reducing the Dimensionality of Data with Neural Networks. Science, 313(5786), 504–507. DOI ↗ | LeCun, Y., Bottou, L., Bengio, Y. & Haffner, P. (1998). Gradient-Based Learning Applied to Document Recognition. Proceedings of the IEEE, 86(11), 2278–2324. DOI ↗ | Breiman, L. (2001). Random Forests. Machine Learning, 45, 5–32. DOI ↗ |
| Aliassen | Otokodlayıcı (Autoencoder), otokodlayıcı, auto-encoder, encoder-decoder network | CNN (Evrişimli Sinir Ağı — Sınıflandırma), CNN classification, ConvNet, convolutional network classifier | Rastgele Orman (Random Forest), rastgele orman, random decision forest, bagged tree ensemble |
| Verwant≠ | 4 | 5 | 4 |
| Samenvatting≠ | 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 Convolutional Neural Network (CNN) is a deep learning model, established by LeCun and colleagues in 1998, that learns local patterns directly from images and structured data to classify them. Stacks of convolutional filters discover increasingly abstract features, so manual feature engineering can be largely reduced. | Random Forest is an ensemble learning method, introduced by Leo Breiman in 2001, that grows many decision trees on bootstrap samples of the data and combines their votes to produce strong classification and regression. By pooling many slightly different trees, it produces more accurate and more stable predictions than any single tree. |
| ScholarGateGegevensset ↗ |
|
|
|