So sánh phương pháp

	Mạng Capsule	Chưng cất tri thức	Tìm kiếm Kiến trúc Mạng Nơ-ron	Rừng ngẫu nhiên
Lĩnh vực	Học sâu	Học sâu	Học sâu	Học máy
Họ	Machine learning	Machine learning	Machine learning	Machine learning
Năm ra đời	2017	2015	2017	2001
Người khởi xướng	Sabour, S., Frosst, N. & Hinton, G. E.	Hinton, G., Vinyals, O. & Dean, J.	Zoph, B. & Le, Q.V.	Breiman, L.
Loại	Deep learning architecture (vector capsules with dynamic routing)	Neural network compression (teacher–student)	Automated architecture optimization (deep learning)	Ensemble (bagging of decision trees)
Công trình gốc	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.	Zoph, B. & Le, Q.V. (2017). Neural Architecture Search with Reinforcement Learning. ICLR.	Breiman, L. (2001). Random Forests. Machine Learning, 45, 5–32.
Tên gọi khác	Kapsül Ağı (CapsNet), CapsNet, capsule net, dynamic routing network	Bilgi Damıtma (Knowledge Distillation), bilgi damıtma, teacher-student distillation, model distillation	Nöral Mimari Arama (NAS), NAS, automated architecture design, differentiable architecture search	Rastgele Orman (Random Forest), rastgele orman, random decision forest, bagged tree ensemble
Liên quan	4	5	5	4
Tóm tắt	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.	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.	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.