Compară metode

	Distilarea cunoștințelor	Descrierea algoritmului de optimizare Gradient Descent Stocastic (SGD)
Domeniu	Învățare profundă	Învățare automată
Familie	Machine learning	Machine learning
Anul apariției	2015	1951
Autorul original	Hinton, G., Vinyals, O. & Dean, J.	Robbins, H. & Monro, S.
Tip	Neural network compression (teacher–student)	First-order iterative optimization algorithm
Sursa seminală	Hinton, G., Vinyals, O. & Dean, J. (2015). Distilling the Knowledge in a Neural Network. NeurIPS Deep Learning Workshop.	Robbins, H. & Monro, S. (1951). A Stochastic Approximation Method. The Annals of Mathematical Statistics, 22(3), 400–407.
Denumiri alternative	Bilgi Damıtma (Knowledge Distillation), bilgi damıtma, teacher-student distillation, model distillation	SGD, online gradient descent, incremental gradient descent, mini-batch gradient descent
Înrudite	5	3
Rezumat	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.	Stochastic Gradient Descent (SGD) is a first-order iterative optimization algorithm, rooted in the stochastic approximation framework introduced by Robbins and Monro in 1951, that minimizes an objective function by updating model parameters using the gradient computed on a single randomly selected training example (or a small mini-batch) at each step. It is the core optimization engine behind modern machine learning and deep learning, enabling the training of models on datasets too large to fit in memory.