Σύγκριση μεθόδων

	Δίκτυο Κάψουλας	Μηχανή Υποστήριξης Διανυσμάτων (Ταξινόμηση)
Πεδίο	Βαθιά Μάθηση	Μηχανική Μάθηση
Οικογένεια	Machine learning	Machine learning
Έτος προέλευσης	2017	1995
Δημιουργός	Sabour, S., Frosst, N. & Hinton, G. E.	Cortes, C. & Vapnik, V.
Τύπος	Deep learning architecture (vector capsules with dynamic routing)	Maximum-margin classifier (kernel method)
Θεμελιώδης πηγή	Sabour, S., Frosst, N. & Hinton, G. E. (2017). Dynamic Routing Between Capsules. Advances in Neural Information Processing Systems (NeurIPS).	Cortes, C. & Vapnik, V. (1995). Support-Vector Networks. Machine Learning, 20, 273–297.
Εναλλακτικές ονομασίες	Kapsül Ağı (CapsNet), CapsNet, capsule net, dynamic routing network	Destek Vektör Makinesi (SVM — Sınıflandırma), support-vector network, SVM classifier, maximum-margin classifier
Συναφείς	4	5
Σύνοψη	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.	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.