手法を比較

	カプセルネットワーク	ニューラルアーキテクチャ探索
分野	深層学習	深層学習
系統	Machine learning	Machine learning
提唱年	2017	2017
提唱者	Sabour, S., Frosst, N. & Hinton, G. E.	Zoph, B. & Le, Q.V.
種類	Deep learning architecture (vector capsules with dynamic routing)	Automated architecture optimization (deep learning)
原典	Sabour, S., Frosst, N. & Hinton, G. E. (2017). Dynamic Routing Between Capsules. Advances in Neural Information Processing Systems (NeurIPS).	Zoph, B. & Le, Q.V. (2017). Neural Architecture Search with Reinforcement Learning. ICLR.
別名	Kapsül Ağı (CapsNet), CapsNet, capsule net, dynamic routing network	Nöral Mimari Arama (NAS), NAS, automated architecture design, differentiable architecture search
関連	4	5
概要	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.	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.