ScholarGate
Assistent

Võrdle meetodeid

Vaata valitud meetodeid kõrvuti; erinevad read on esile tõstetud.

Neuraalarhitektuuri otsing×Teadmise destilleerimine×
ValdkondSüvaõpeSüvaõpe
PerekondMachine learningMachine learning
Tekkeaasta20172015
LoojaZoph, B. & Le, Q.V.Hinton, G., Vinyals, O. & Dean, J.
TüüpAutomated architecture optimization (deep learning)Neural network compression (teacher–student)
AlgallikasZoph, 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 ↗
RööpnimetusedNöral Mimari Arama (NAS), NAS, automated architecture design, differentiable architecture searchBilgi Damıtma (Knowledge Distillation), bilgi damıtma, teacher-student distillation, model distillation
Seotud55
KokkuvõteNeural 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.
ScholarGateAndmestik
  1. v1
  2. 2 Allikad
  3. PUBLISHED
  1. v1
  2. 2 Allikad
  3. PUBLISHED

Mine otsingusse Laadi slaidid alla

ScholarGateVõrdle meetodeid: Neural Architecture Search · Knowledge Distillation. Loetud 2026-06-18 aadressilt https://scholargate.app/et/compare