方法证据记录
Capsule Network
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.
源记录
引文逐字复制自方法源记录。这些引文不代表任何层级的验证。
Capsule Network (CapsNet)
分类方法记录 · ml-model / deep-learning
- Sabour, S., Frosst, N. & Hinton, G. E. (2017). Dynamic Routing Between Capsules. Advances in Neural Information Processing Systems (NeurIPS). · URL
- Hinton, G. E., Sabour, S. & Frosst, N. (2018). Matrix Capsules with EM Routing. International Conference on Learning Representations (ICLR). · URL
精选声明
声明已持久化到证据分类账中，每个声明都有自己的评估。
尚无精选声明
当分类账中没有声明时，此视图不会自行创建声明评估。
相关方法
从方法图中生成，显示为机器建议的关系 — 不推断任何证据声明。