Porovnat metody
Prohlédněte si vybrané metody vedle sebe; řádky, které se liší, jsou zvýrazněny.
| Destilace znalostí× | Stroj s podpůrnými vektory (klasifikace)× | |
|---|---|---|
| Obor≠ | Hluboké učení | Strojové učení |
| Rodina | Machine learning | Machine learning |
| Rok vzniku≠ | 2015 | 1995 |
| Tvůrce≠ | Hinton, G., Vinyals, O. & Dean, J. | Cortes, C. & Vapnik, V. |
| Typ≠ | Neural network compression (teacher–student) | 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 ↗ | 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 | Destek Vektör Makinesi (SVM — Sınıflandırma), support-vector network, SVM classifier, maximum-margin classifier |
| Příbuzné | 5 | 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. | 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 ↗ |
|
|