Comparer des méthodes
Examinez les méthodes sélectionnées côte à côte ; les lignes qui diffèrent sont mises en évidence.
| Distillation de connaissances× | Recherche d'architecture neuronale× | |
|---|---|---|
| Domaine | Apprentissage profond | Apprentissage profond |
| Famille | Machine learning | Machine learning |
| Année d'origine≠ | 2015 | 2017 |
| Auteur d'origine≠ | Hinton, G., Vinyals, O. & Dean, J. | Zoph, B. & Le, Q.V. |
| Type≠ | Neural network compression (teacher–student) | Automated architecture optimization (deep learning) |
| Source fondatrice≠ | 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 ↗ |
| Alias | Bilgi Damıtma (Knowledge Distillation), bilgi damıtma, teacher-student distillation, model distillation | Nöral Mimari Arama (NAS), NAS, automated architecture design, differentiable architecture search |
| 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. | 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. |
| ScholarGateJeu de données ↗ |
|
|