قارن الطرق

	تقطير المعرفة	آلة المتجهات الداعمة (التصنيف)
المجال	التعلم العميق	تعلم الآلة
العائلة	Machine learning	Machine learning
سنة النشأة	2015	1995
صاحب الطريقة	Hinton, G., Vinyals, O. & Dean, J.	Cortes, C. & Vapnik, V.
النوع	Neural network compression (teacher–student)	Maximum-margin classifier (kernel method)
المصدر التأسيسي	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.
الأسماء البديلة	Bilgi Damıtma (Knowledge Distillation), bilgi damıtma, teacher-student distillation, model distillation	Destek Vektör Makinesi (SVM — Sınıflandırma), support-vector network, SVM classifier, maximum-margin classifier
ذات صلة	5	5
الملخص	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.