Salīdzināt metodes
Apskatiet izvēlētās metodes blakus; rindas, kas atšķiras, ir izceltas.
| Kapsulu tīkls× | Neirālā arhitektūras meklēšana× | Atbalsta vektoru mašīna (klasifikācija)× | |
|---|---|---|---|
| Nozare≠ | Dziļā mācīšanās | Dziļā mācīšanās | Mašīnmācīšanās |
| Saime | Machine learning | Machine learning | Machine learning |
| Izcelsmes gads≠ | 2017 | 2017 | 1995 |
| Autors≠ | Sabour, S., Frosst, N. & Hinton, G. E. | Zoph, B. & Le, Q.V. | Cortes, C. & Vapnik, V. |
| Tips≠ | Deep learning architecture (vector capsules with dynamic routing) | Automated architecture optimization (deep learning) | Maximum-margin classifier (kernel method) |
| Pirmavots≠ | Sabour, S., Frosst, N. & Hinton, G. E. (2017). Dynamic Routing Between Capsules. Advances in Neural Information Processing Systems (NeurIPS). link ↗ | Zoph, B. & Le, Q.V. (2017). Neural Architecture Search with Reinforcement Learning. ICLR. link ↗ | Cortes, C. & Vapnik, V. (1995). Support-Vector Networks. Machine Learning, 20, 273–297. DOI ↗ |
| Citi nosaukumi | Kapsül Ağı (CapsNet), CapsNet, capsule net, dynamic routing network | Nöral Mimari Arama (NAS), NAS, automated architecture design, differentiable architecture search | Destek Vektör Makinesi (SVM — Sınıflandırma), support-vector network, SVM classifier, maximum-margin classifier |
| Saistītās≠ | 4 | 5 | 5 |
| Kopsavilkums≠ | 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. | 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. |
| ScholarGateDatu kopa ↗ |
|
|
|