ScholarGate
Asistent

Compară metode

Examinează metodele selectate una lângă alta; rândurile care diferă sunt evidențiate.

Distilarea cunoștințelor×XGBoost×
DomeniuÎnvățare profundăÎnvățare automată
FamilieMachine learningMachine learning
Anul apariției20152016
Autorul originalHinton, G., Vinyals, O. & Dean, J.Chen, T. & Guestrin, C.
TipNeural network compression (teacher–student)Ensemble (gradient-boosted decision trees)
Sursa seminalăHinton, G., Vinyals, O. & Dean, J. (2015). Distilling the Knowledge in a Neural Network. NeurIPS Deep Learning Workshop. link ↗Chen, T. & Guestrin, C. (2016). XGBoost: A Scalable Tree Boosting System. Proceedings of the 22nd ACM SIGKDD, 785–794. DOI ↗
Denumiri alternativeBilgi Damıtma (Knowledge Distillation), bilgi damıtma, teacher-student distillation, model distillationXGBoost, extreme gradient boosting, scalable tree boosting
Înrudite55
RezumatKnowledge 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.XGBoost (Extreme Gradient Boosting) is a scalable tree-boosting algorithm introduced by Tianqi Chen and Carlos Guestrin in 2016. It builds a strong predictor by adding decision trees one at a time, each correcting the errors left by the trees before it, and is a powerful prediction method widely used in competitions.
ScholarGateSet de date
  1. v1
  2. 2 Surse
  3. PUBLISHED
  1. v1
  2. 1 Surse
  3. PUBLISHED

Mergi la căutare Descarcă prezentarea

ScholarGateCompară metode: Knowledge Distillation · XGBoost. Preluat la 2026-06-17 de pe https://scholargate.app/ro/compare