Porównaj metody
Przeglądaj wybrane metody obok siebie; wiersze, które się różnią, są wyróżnione.
| Destylacja wiedzy× | Automatyczne wyszukiwanie architektury sieci neuronowych× | |
|---|---|---|
| Dziedzina | Uczenie głębokie | Uczenie głębokie |
| Rodzina | Machine learning | Machine learning |
| Rok powstania≠ | 2015 | 2017 |
| Twórca≠ | Hinton, G., Vinyals, O. & Dean, J. | Zoph, B. & Le, Q.V. |
| Typ≠ | Neural network compression (teacher–student) | Automated architecture optimization (deep learning) |
| Źródło pierwotne≠ | Hinton, G., Vinyals, O. & Dean, J. (2015). Distilling the Knowledge in a Neural Network. NeurIPS Deep Learning Workshop. link ↗ | Zoph, B. & Le, Q.V. (2017). Neural Architecture Search with Reinforcement Learning. ICLR. link ↗ |
| Inne nazwy | Bilgi Damıtma (Knowledge Distillation), bilgi damıtma, teacher-student distillation, model distillation | Nöral Mimari Arama (NAS), NAS, automated architecture design, differentiable architecture search |
| Pokrewne | 5 | 5 |
| Podsumowanie≠ | 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. | Neural Architecture Search (NAS), introduced by Zoph and Le in 2017, automatically optimizes architectural decisions such as a network's depth, width, and connection structure instead of hand-designing them. Leading methods in the field include DARTS, ENAS, and Once-for-All. |
| ScholarGateZbiór danych ↗ |
|
|