Сравнение методов

	Капсульная сеть	Дистилляция знаний	Случайный лес
Область	Глубокое обучение	Глубокое обучение	Машинное обучение
Семейство	Machine learning	Machine learning	Machine learning
Год появления	2017	2015	2001
Автор метода	Sabour, S., Frosst, N. & Hinton, G. E.	Hinton, G., Vinyals, O. & Dean, J.	Breiman, L.
Тип	Deep learning architecture (vector capsules with dynamic routing)	Neural network compression (teacher–student)	Ensemble (bagging of decision trees)
Основополагающий источник	Sabour, S., Frosst, N. & Hinton, G. E. (2017). Dynamic Routing Between Capsules. Advances in Neural Information Processing Systems (NeurIPS).	Hinton, G., Vinyals, O. & Dean, J. (2015). Distilling the Knowledge in a Neural Network. NeurIPS Deep Learning Workshop.	Breiman, L. (2001). Random Forests. Machine Learning, 45, 5–32.
Другие названия	Kapsül Ağı (CapsNet), CapsNet, capsule net, dynamic routing network	Bilgi Damıtma (Knowledge Distillation), bilgi damıtma, teacher-student distillation, model distillation	Rastgele Orman (Random Forest), rastgele orman, random decision forest, bagged tree ensemble
Связанные	4	5	4
Сводка	A Capsule Network (CapsNet) is a deep learning architecture introduced by Sara Sabour, Nicholas Frosst and Geoffrey Hinton in 2017 that organises neurons as vectors (capsules) rather than scalar activations, so that spatial hierarchy and pose (orientation) information are encoded directly. It was proposed to overcome the fragility of convolutional networks to changes in viewpoint.	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.	Random Forest is an ensemble learning method, introduced by Leo Breiman in 2001, that grows many decision trees on bootstrap samples of the data and combines their votes to produce strong classification and regression. By pooling many slightly different trees, it produces more accurate and more stable predictions than any single tree.