ScholarGate
Асистент

Сравнение на методи

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

Дестилация на знания×Методът на опорните вектори (класификация)×
ОбластДълбоко обучениеМашинно обучение
СемействоMachine learningMachine learning
Година на възникване20151995
СъздателHinton, G., Vinyals, O. & Dean, J.Cortes, C. & Vapnik, V.
ТипNeural network compression (teacher–student)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 ↗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 distillationDestek Vektör Makinesi (SVM — Sınıflandırma), support-vector network, SVM classifier, maximum-margin classifier
Свързани55
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.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. 1 Източници
  3. PUBLISHED

Към търсенето Изтегляне на слайдове

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