방법 비교
선택한 방법을 나란히 검토하세요. 서로 다른 행은 강조 표시됩니다.
| 지식 증류× | 전이 학습× | |
|---|---|---|
| 분야≠ | 딥러닝 | 머신러닝 |
| 계열 | Machine learning | Machine learning |
| 기원 연도≠ | 2015 | 2010 (formalized); 1990s (early roots) |
| 창시자≠ | Hinton, G., Vinyals, O. & Dean, J. | Pan, S. J. & Yang, Q. (survey); Bengio, Y. (deep learning framing) |
| 유형≠ | Neural network compression (teacher–student) | Learning paradigm |
| 원전≠ | Hinton, G., Vinyals, O. & Dean, J. (2015). Distilling the Knowledge in a Neural Network. NeurIPS Deep Learning Workshop. link ↗ | Pan, S. J., & Yang, Q. (2010). A Survey on Transfer Learning. IEEE Transactions on Knowledge and Data Engineering, 22(10), 1345–1359. DOI ↗ |
| 별칭 | Bilgi Damıtma (Knowledge Distillation), bilgi damıtma, teacher-student distillation, model distillation | TL, domain adaptation, fine-tuning, pre-trained model adaptation |
| 관련≠ | 5 | 3 |
| 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. | Transfer learning is a machine learning paradigm in which knowledge gained from training a model on a source task or domain is reused to improve learning on a different but related target task or domain. It is especially powerful when labeled data for the target task is scarce, and it underlies most modern deep learning applications in computer vision, natural language processing, and beyond. |
| ScholarGate데이터셋 ↗ |
|
|