विधियों की तुलना करें

	नॉलेज डिस्टिलेशन	सपोर्ट वेक्टर मशीन (वर्गीकरण)
क्षेत्र	गहन अधिगम	मशीन अधिगम
परिवार	Machine learning	Machine learning
उद्भव वर्ष	2015	1995
प्रवर्तक	Hinton, G., Vinyals, O. & Dean, J.	Cortes, C. & Vapnik, V.
प्रकार	Neural network compression (teacher–student)	Maximum-margin classifier (kernel method)
मौलिक स्रोत	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.
उपनाम	Bilgi Damıtma (Knowledge Distillation), bilgi damıtma, teacher-student distillation, model distillation	Destek Vektör Makinesi (SVM — Sınıflandırma), support-vector network, SVM classifier, maximum-margin classifier
संबंधित	5	5
सारांश	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.