Porovnat metody
Prohlédněte si vybrané metody vedle sebe; řádky, které se liší, jsou zvýrazněny.
| Konvoluční neuronová síť (klasifikace)× | Random Forest× | Stroj s podpůrnými vektory (klasifikace)× | |
|---|---|---|---|
| Obor≠ | Hluboké učení | Strojové učení | Strojové učení |
| Rodina | Machine learning | Machine learning | Machine learning |
| Rok vzniku≠ | 1998 | 2001 | 1995 |
| Tvůrce≠ | LeCun, Y. et al. | Breiman, L. | Cortes, C. & Vapnik, V. |
| Typ≠ | Deep neural network (convolutional) | Ensemble (bagging of decision trees) | Maximum-margin classifier (kernel method) |
| Původní zdroj≠ | 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 ↗ | Cortes, C. & Vapnik, V. (1995). Support-Vector Networks. Machine Learning, 20, 273–297. DOI ↗ |
| Další názvy | CNN (Evrişimli Sinir Ağı — Sınıflandırma), CNN classification, ConvNet, convolutional network classifier | Rastgele Orman (Random Forest), rastgele orman, random decision forest, bagged tree ensemble | Destek Vektör Makinesi (SVM — Sınıflandırma), support-vector network, SVM classifier, maximum-margin classifier |
| Příbuzné≠ | 5 | 4 | 5 |
| Shrnutí≠ | 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. | The Support Vector Machine, introduced by Corinna Cortes and Vladimir Vapnik in 1995, is a classifier that finds the optimal separating hyperplane between classes in a high-dimensional space. It chooses the boundary that leaves the widest possible margin to the nearest training points, which makes its decisions robust on new data. |
| ScholarGateDatová sada ↗ |
|
|
|