ScholarGate
Ассистент

Сравнение методов

Просматривайте выбранные методы рядом; строки с различиями подсвечены.

Дистилляция знаний×Нейросетевой поиск архитектур×
ОбластьГлубокое обучениеГлубокое обучение
СемействоMachine learningMachine learning
Год появления20152017
Автор методаHinton, G., Vinyals, O. & Dean, J.Zoph, B. & Le, Q.V.
ТипNeural network compression (teacher–student)Automated architecture optimization (deep learning)
Основополагающий источникHinton, 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 ↗
Другие названияBilgi Damıtma (Knowledge Distillation), bilgi damıtma, teacher-student distillation, model distillationNöral Mimari Arama (NAS), NAS, automated architecture design, differentiable architecture search
Связанные55
СводкаKnowledge 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.
ScholarGateНабор данных
  1. v1
  2. 2 Источники
  3. PUBLISHED
  1. v1
  2. 2 Источники
  3. PUBLISHED

Перейти к поиску Скачать слайды

ScholarGateСравнение методов: Knowledge Distillation · Neural Architecture Search. Получено 2026-06-19 из https://scholargate.app/ru/compare