Sammenlign metoder
Gjennomgå de valgte metodene side om side; rader som avviker, er uthevet.
| Kunnskapsdestillasjon× | Nevral arkitektursøk× | |
|---|---|---|
| Fagfelt | Dyp læring | Dyp læring |
| Familie | Machine learning | Machine learning |
| Opprinnelsesår≠ | 2015 | 2017 |
| Opphavsperson≠ | Hinton, G., Vinyals, O. & Dean, J. | Zoph, B. & Le, Q.V. |
| Type≠ | Neural network compression (teacher–student) | Automated architecture optimization (deep learning) |
| Opprinnelig kilde≠ | 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 |
| Relaterte | 5 | 5 |
| Sammendrag≠ | 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. |
| ScholarGateDatasett ↗ |
|
|