ScholarGate
Asistent

Compară metode

Examinează metodele selectate una lângă alta; rândurile care diferă sunt evidențiate.

Căutarea Arhitecturilor Neuronale×Distilarea cunoștințelor×
DomeniuÎnvățare profundăÎnvățare profundă
FamilieMachine learningMachine learning
Anul apariției20172015
Autorul originalZoph, B. & Le, Q.V.Hinton, G., Vinyals, O. & Dean, J.
TipAutomated architecture optimization (deep learning)Neural network compression (teacher–student)
Sursa seminalăZoph, 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 ↗
Denumiri alternativeNöral Mimari Arama (NAS), NAS, automated architecture design, differentiable architecture searchBilgi Damıtma (Knowledge Distillation), bilgi damıtma, teacher-student distillation, model distillation
Înrudite55
RezumatNeural 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.
ScholarGateSet de date
  1. v1
  2. 2 Surse
  3. PUBLISHED
  1. v1
  2. 2 Surse
  3. PUBLISHED

Mergi la căutare Descarcă prezentarea

ScholarGateCompară metode: Neural Architecture Search · Knowledge Distillation. Preluat la 2026-06-18 de pe https://scholargate.app/ro/compare