Usporedite metode
Pregledajte odabrane metode jednu uz drugu; retci koji se razlikuju su istaknuti.
| Destilacija znanja× | Stroj potpornih vektora (klasifikacija)× | |
|---|---|---|
| Područje≠ | Duboko učenje | Strojno učenje |
| Obitelj | Machine learning | Machine learning |
| Godina nastanka≠ | 2015 | 1995 |
| Tvorac≠ | Hinton, G., Vinyals, O. & Dean, J. | Cortes, C. & Vapnik, V. |
| Vrsta≠ | Neural network compression (teacher–student) | Maximum-margin classifier (kernel method) |
| Temeljni izvor≠ | 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 ↗ |
| Drugi nazivi | Bilgi Damıtma (Knowledge Distillation), bilgi damıtma, teacher-student distillation, model distillation | Destek Vektör Makinesi (SVM — Sınıflandırma), support-vector network, SVM classifier, maximum-margin classifier |
| Srodne | 5 | 5 |
| Sažetak≠ | 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. |
| ScholarGateSkup podataka ↗ |
|
|