Comparar métodos

	Destilação de Conhecimento	XGBoost
Área	Aprendizado profundo	Aprendizado de máquina
Família	Machine learning	Machine learning
Ano de origem	2015	2016
Autor original	Hinton, G., Vinyals, O. & Dean, J.	Chen, T. & Guestrin, C.
Tipo	Neural network compression (teacher–student)	Ensemble (gradient-boosted decision trees)
Fonte seminal	Hinton, G., Vinyals, O. & Dean, J. (2015). Distilling the Knowledge in a Neural Network. NeurIPS Deep Learning Workshop.	Chen, T. & Guestrin, C. (2016). XGBoost: A Scalable Tree Boosting System. Proceedings of the 22nd ACM SIGKDD, 785–794.
Outros nomes	Bilgi Damıtma (Knowledge Distillation), bilgi damıtma, teacher-student distillation, model distillation	XGBoost, extreme gradient boosting, scalable tree boosting
Relacionados	5	5
Resumo	Knowledge 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.