Porovnat metody
Prohlédněte si vybrané metody vedle sebe; řádky, které se liší, jsou zvýrazněny.
| Destilace znalostí× | Random Forest× | Stroj s podpůrnými vektory (klasifikace)× | |
|---|---|---|---|
| Obor≠ | Hluboké učení | Strojové učení | Strojové učení |
| Rodina | Machine learning | Machine learning | Machine learning |
| Rok vzniku≠ | 2015 | 2001 | 1995 |
| Tvůrce≠ | Hinton, G., Vinyals, O. & Dean, J. | Breiman, L. | Cortes, C. & Vapnik, V. |
| Typ≠ | Neural network compression (teacher–student) | Ensemble (bagging of decision trees) | Maximum-margin classifier (kernel method) |
| Původní zdroj≠ | Hinton, G., Vinyals, O. & Dean, J. (2015). Distilling the Knowledge in a Neural Network. NeurIPS Deep Learning Workshop. link ↗ | 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 | Bilgi Damıtma (Knowledge Distillation), bilgi damıtma, teacher-student distillation, model distillation | 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≠ | Knowledge Distillation is a model-compression technique, introduced by Geoffrey Hinton and colleagues in 2015, that trains a small student model using the soft-label outputs of a large teacher model. Distilled models such as DistilBERT and TinyBERT reach roughly 97% of the larger model's performance while running far faster. | 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 ↗ |
|
|
|