방법 비교
선택한 방법을 나란히 검토하세요. 서로 다른 행은 강조 표시됩니다.
| 지식 증류× | 서포트 벡터 머신 (분류)× | |
|---|---|---|
| 분야≠ | 딥러닝 | 머신러닝 |
| 계열 | Machine learning | Machine learning |
| 기원 연도≠ | 2015 | 1995 |
| 창시자≠ | Hinton, G., Vinyals, O. & Dean, J. | Cortes, C. & Vapnik, V. |
| 유형≠ | Neural network compression (teacher–student) | Maximum-margin classifier (kernel method) |
| 원전≠ | 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 ↗ |
| 별칭 | Bilgi Damıtma (Knowledge Distillation), bilgi damıtma, teacher-student distillation, model distillation | Destek Vektör Makinesi (SVM — Sınıflandırma), support-vector network, SVM classifier, maximum-margin classifier |
| 관련 | 5 | 5 |
| 요약≠ | 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. |
| ScholarGate데이터셋 ↗ |
|
|