ScholarGate
Assistent

Sammenlign metoder

Gennemgå dine valgte metoder side om side; rækker, der afviger, er fremhævet.

Knowledge Distillation×Neural Architecture Search×
FagområdeDyb læringDyb læring
FamilieMachine learningMachine learning
Oprindelsesår20152017
OphavspersonHinton, G., Vinyals, O. & Dean, J.Zoph, B. & Le, Q.V.
TypeNeural network compression (teacher–student)Automated architecture optimization (deep learning)
Oprindelig kildeHinton, 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 ↗
AliasserBilgi Damıtma (Knowledge Distillation), bilgi damıtma, teacher-student distillation, model distillationNöral Mimari Arama (NAS), NAS, automated architecture design, differentiable architecture search
Relaterede55
ResuméKnowledge 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.
ScholarGateDatasæt
  1. v1
  2. 2 Kilder
  3. PUBLISHED
  1. v1
  2. 2 Kilder
  3. PUBLISHED

Gå til søgning Hent slides

ScholarGateSammenlign metoder: Knowledge Distillation · Neural Architecture Search. Hentet 2026-06-19 fra https://scholargate.app/da/compare