Comparer des méthodes
Examinez les méthodes sélectionnées côte à côte ; les lignes qui diffèrent sont mises en évidence.
| Distillation de connaissances× | Machine à vecteurs de support (Classification)× | |
|---|---|---|
| Domaine≠ | Apprentissage profond | Apprentissage automatique |
| Famille | Machine learning | Machine learning |
| Année d'origine≠ | 2015 | 1995 |
| Auteur d'origine≠ | Hinton, G., Vinyals, O. & Dean, J. | Cortes, C. & Vapnik, V. |
| Type≠ | Neural network compression (teacher–student) | Maximum-margin classifier (kernel method) |
| Source fondatrice≠ | 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 ↗ |
| Alias | Bilgi Damıtma (Knowledge Distillation), bilgi damıtma, teacher-student distillation, model distillation | Destek Vektör Makinesi (SVM — Sınıflandırma), support-vector network, SVM classifier, maximum-margin classifier |
| Apparentées | 5 | 5 |
| Résumé≠ | 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. |
| ScholarGateJeu de données ↗ |
|
|