ScholarGate
Асистент

Сравнение на методи

Прегледайте избраните методи един до друг; редовете с разлики са откроени.

Дестилация на знания×Търсене на невронни архитектури×Методът на опорните вектори (класификация)×
ОбластДълбоко обучениеДълбоко обучениеМашинно обучение
СемействоMachine learningMachine learningMachine learning
Година на възникване201520171995
СъздателHinton, G., Vinyals, O. & Dean, J.Zoph, B. & Le, Q.V.Cortes, C. & Vapnik, V.
ТипNeural network compression (teacher–student)Automated architecture optimization (deep learning)Maximum-margin classifier (kernel method)
Основополагащ източникHinton, 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 ↗Cortes, C. & Vapnik, V. (1995). Support-Vector Networks. Machine Learning, 20, 273–297. DOI ↗
Други названияBilgi Damıtma (Knowledge Distillation), bilgi damıtma, teacher-student distillation, model distillationNöral Mimari Arama (NAS), NAS, automated architecture design, differentiable architecture searchDestek Vektör Makinesi (SVM — Sınıflandırma), support-vector network, SVM classifier, maximum-margin classifier
Свързани555
РезюмеKnowledge 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.The Support Vector Machine, introduced by Corinna Cortes and Vladimir Vapnik in 1995, is a classifier that finds the optimal separating hyperplane between classes in a high-dimensional space. It chooses the boundary that leaves the widest possible margin to the nearest training points, which makes its decisions robust on new data.
ScholarGateНабор от данни
  1. v1
  2. 2 Източници
  3. PUBLISHED
  1. v1
  2. 2 Източници
  3. PUBLISHED
  1. v1
  2. 1 Източници
  3. PUBLISHED

Към търсенето Изтегляне на слайдове

ScholarGateСравнение на методи: Knowledge Distillation · Neural Architecture Search · Support Vector Machine. Извлечено на 2026-06-19 от https://scholargate.app/bg/compare