Linganisha mbinu

	Ufumbuzi wa Maarifa	Utafutaji wa Usanifu wa Neural	Support Vector Machine (Uainishaji)
Nyanja	Ujifunzaji wa Kina	Ujifunzaji wa Kina	Ujifunzaji wa Mashine
Familia	Machine learning	Machine learning	Machine learning
Mwaka wa asili	2015	2017	1995
Mwanzilishi	Hinton, G., Vinyals, O. & Dean, J.	Zoph, B. & Le, Q.V.	Cortes, C. & Vapnik, V.
Aina	Neural network compression (teacher–student)	Automated architecture optimization (deep learning)	Maximum-margin classifier (kernel method)
Chanzo asilia	Hinton, G., Vinyals, O. & Dean, J. (2015). Distilling the Knowledge in a Neural Network. NeurIPS Deep Learning Workshop.	Zoph, B. & Le, Q.V. (2017). Neural Architecture Search with Reinforcement Learning. ICLR.	Cortes, C. & Vapnik, V. (1995). Support-Vector Networks. Machine Learning, 20, 273–297.
Majina mbadala	Bilgi Damıtma (Knowledge Distillation), bilgi damıtma, teacher-student distillation, model distillation	Nöral Mimari Arama (NAS), NAS, automated architecture design, differentiable architecture search	Destek Vektör Makinesi (SVM — Sınıflandırma), support-vector network, SVM classifier, maximum-margin classifier
Zinazohusiana	5	5	5
Muhtasari	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.	Neural Architecture Search (NAS), introduced by Zoph and Le in 2017, automatically optimizes architectural decisions such as a network's depth, width, and connection structure instead of hand-designing them. Leading methods in the field include DARTS, ENAS, and Once-for-All.	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.