ScholarGate
Asystent

Porównaj metody

Przeglądaj wybrane metody obok siebie; wiersze, które się różnią, są wyróżnione.

Destylacja wiedzy×Maszyna wektorów nośnych (klasyfikacja)×
DziedzinaUczenie głębokieUczenie maszynowe
RodzinaMachine learningMachine learning
Rok powstania20151995
TwórcaHinton, G., Vinyals, O. & Dean, J.Cortes, C. & Vapnik, V.
TypNeural network compression (teacher–student)Maximum-margin classifier (kernel method)
Źródło pierwotneHinton, 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 ↗
Inne nazwyBilgi Damıtma (Knowledge Distillation), bilgi damıtma, teacher-student distillation, model distillationDestek Vektör Makinesi (SVM — Sınıflandırma), support-vector network, SVM classifier, maximum-margin classifier
Pokrewne55
PodsumowanieKnowledge 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.
ScholarGateZbiór danych
  1. v1
  2. 2 Źródła
  3. PUBLISHED
  1. v1
  2. 1 Źródła
  3. PUBLISHED

Przejdź do wyszukiwania Pobierz slajdy

ScholarGatePorównaj metody: Knowledge Distillation · Support Vector Machine. Pobrano 2026-06-19 z https://scholargate.app/pl/compare