ScholarGate
Asystent

Porównaj metody

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

Automatyczne wyszukiwanie architektury sieci neuronowych×Destylacja wiedzy×
DziedzinaUczenie głębokieUczenie głębokie
RodzinaMachine learningMachine learning
Rok powstania20172015
TwórcaZoph, B. & Le, Q.V.Hinton, G., Vinyals, O. & Dean, J.
TypAutomated architecture optimization (deep learning)Neural network compression (teacher–student)
Źródło pierwotneZoph, B. & Le, Q.V. (2017). Neural Architecture Search with Reinforcement Learning. ICLR. link ↗Hinton, G., Vinyals, O. & Dean, J. (2015). Distilling the Knowledge in a Neural Network. NeurIPS Deep Learning Workshop. link ↗
Inne nazwyNöral Mimari Arama (NAS), NAS, automated architecture design, differentiable architecture searchBilgi Damıtma (Knowledge Distillation), bilgi damıtma, teacher-student distillation, model distillation
Pokrewne55
PodsumowanieNeural 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.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.
ScholarGateZbiór danych
  1. v1
  2. 2 Źródła
  3. PUBLISHED
  1. v1
  2. 2 Źródła
  3. PUBLISHED

Przejdź do wyszukiwania Pobierz slajdy

ScholarGatePorównaj metody: Neural Architecture Search · Knowledge Distillation. Pobrano 2026-06-18 z https://scholargate.app/pl/compare