So sánh phương pháp

	Chưng cất tri thức	Máy Vectơ Hỗ trợ (Phân loại)
Lĩnh vực	Học sâu	Học máy
Họ	Machine learning	Machine learning
Năm ra đời	2015	1995
Người khởi xướng	Hinton, G., Vinyals, O. & Dean, J.	Cortes, C. & Vapnik, V.
Loại	Neural network compression (teacher–student)	Maximum-margin classifier (kernel method)
Công trình gốc	Hinton, G., Vinyals, O. & Dean, J. (2015). Distilling the Knowledge in a Neural Network. NeurIPS Deep Learning Workshop.	Cortes, C. & Vapnik, V. (1995). Support-Vector Networks. Machine Learning, 20, 273–297.
Tên gọi khác	Bilgi Damıtma (Knowledge Distillation), bilgi damıtma, teacher-student distillation, model distillation	Destek Vektör Makinesi (SVM — Sınıflandırma), support-vector network, SVM classifier, maximum-margin classifier
Liên quan	5	5
Tóm tắt	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.	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.