Comparer des méthodes

	Capsule Network	Forêt Aléatoire
Domaine	Apprentissage profond	Apprentissage automatique
Famille	Machine learning	Machine learning
Année d'origine	2017	2001
Auteur d'origine	Sabour, S., Frosst, N. & Hinton, G. E.	Breiman, L.
Type	Deep learning architecture (vector capsules with dynamic routing)	Ensemble (bagging of decision trees)
Source fondatrice	Sabour, S., Frosst, N. & Hinton, G. E. (2017). Dynamic Routing Between Capsules. Advances in Neural Information Processing Systems (NeurIPS).	Breiman, L. (2001). Random Forests. Machine Learning, 45, 5–32.
Alias	Kapsül Ağı (CapsNet), CapsNet, capsule net, dynamic routing network	Rastgele Orman (Random Forest), rastgele orman, random decision forest, bagged tree ensemble
Apparentées	4	4
Résumé	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.	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.