Porovnať metódy

	Knowledge Distillation	Neúrové vyhľadávanie architektúry
Odbor	Hlboké učenie	Hlboké učenie
Rodina	Machine learning	Machine learning
Rok vzniku	2015	2017
Tvorca	Hinton, G., Vinyals, O. & Dean, J.	Zoph, B. & Le, Q.V.
Typ	Neural network compression (teacher–student)	Automated architecture optimization (deep learning)
Pôvodný zdroj	Hinton, G., Vinyals, O. & Dean, J. (2015). Distilling the Knowledge in a Neural Network. NeurIPS Deep Learning Workshop.	Zoph, B. & Le, Q.V. (2017). Neural Architecture Search with Reinforcement Learning. ICLR.
Ďalšie názvy	Bilgi Damıtma (Knowledge Distillation), bilgi damıtma, teacher-student distillation, model distillation	Nöral Mimari Arama (NAS), NAS, automated architecture design, differentiable architecture search
Príbuzné	5	5
Zhrnutie	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.