ScholarGate
Asistente

Comparar métodos

Revisa los métodos seleccionados uno junto a otro; las filas que difieren aparecen resaltadas.

Destilación de Conocimiento×Máquina de Vectores de Soporte (Clasificación)×
CampoAprendizaje profundoAprendizaje automático
FamiliaMachine learningMachine learning
Año de origen20151995
Autor originalHinton, G., Vinyals, O. & Dean, J.Cortes, C. & Vapnik, V.
TipoNeural network compression (teacher–student)Maximum-margin classifier (kernel method)
Fuente seminalHinton, 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 ↗
AliasBilgi Damıtma (Knowledge Distillation), bilgi damıtma, teacher-student distillation, model distillationDestek Vektör Makinesi (SVM — Sınıflandırma), support-vector network, SVM classifier, maximum-margin classifier
Relacionados55
ResumenKnowledge 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.
ScholarGateConjunto de datos
  1. v1
  2. 2 Fuentes
  3. PUBLISHED
  1. v1
  2. 1 Fuentes
  3. PUBLISHED

Ir a la búsqueda Descargar diapositivas

ScholarGateComparar métodos: Knowledge Distillation · Support Vector Machine. Recuperado el 2026-06-19 de https://scholargate.app/es/compare