ScholarGate
Assistent

Sammenlign metoder

Gjennomgå de valgte metodene side om side; rader som avviker, er uthevet.

Nevral arkitektursøk×Kunnskapsdestillasjon×
FagfeltDyp læringDyp læring
FamilieMachine learningMachine learning
Opprinnelsesår20172015
OpphavspersonZoph, B. & Le, Q.V.Hinton, G., Vinyals, O. & Dean, J.
TypeAutomated architecture optimization (deep learning)Neural network compression (teacher–student)
Opprinnelig kildeZoph, 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 ↗
AliasNöral Mimari Arama (NAS), NAS, automated architecture design, differentiable architecture searchBilgi Damıtma (Knowledge Distillation), bilgi damıtma, teacher-student distillation, model distillation
Relaterte55
SammendragNeural 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.
ScholarGateDatasett
  1. v1
  2. 2 Kilder
  3. PUBLISHED
  1. v1
  2. 2 Kilder
  3. PUBLISHED

Gå til søk Last ned lysbilder

ScholarGateSammenlign metoder: Neural Architecture Search · Knowledge Distillation. Hentet 2026-06-18 fra https://scholargate.app/no/compare