ScholarGate
Asystent

Porównaj metody

Przeglądaj wybrane metody obok siebie; wiersze, które się różnią, są wyróżnione.

Destylacja wiedzy×Automatyczne wyszukiwanie architektury sieci neuronowych×
DziedzinaUczenie głębokieUczenie głębokie
RodzinaMachine learningMachine learning
Rok powstania20152017
TwórcaHinton, G., Vinyals, O. & Dean, J.Zoph, B. & Le, Q.V.
TypNeural network compression (teacher–student)Automated architecture optimization (deep learning)
Źródło pierwotneHinton, 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 nazwyBilgi Damıtma (Knowledge Distillation), bilgi damıtma, teacher-student distillation, model distillationNöral Mimari Arama (NAS), NAS, automated architecture design, differentiable architecture search
Pokrewne55
PodsumowanieKnowledge 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
  1. v1
  2. 2 Źródła
  3. PUBLISHED
  1. v1
  2. 2 Źródła
  3. PUBLISHED

Przejdź do wyszukiwania Pobierz slajdy

ScholarGatePorównaj metody: Knowledge Distillation · Neural Architecture Search. Pobrano 2026-06-19 z https://scholargate.app/pl/compare