Machine learning

胶囊网络

胶囊网络（CapsNet）是Sara Sabour、Nicholas Frosst和Geoffrey Hinton于2017年提出的一种深度学习架构，它将神经元组织成向量（胶囊）而非标量激活，从而直接编码空间层级和姿态（方向）信息。它的提出旨在克服卷积网络对视角变化的脆弱性。

在 MethodMind 中打开即将推出视频即将推出Download slides

阅读完整方法

仅限会员

使用免费账户登录即可阅读本节。

The neighbourhood of related methods — select a node to explore.

胶囊网络

Sabour, S., Frosst, N. & Hinton, G. E. (2017). Dynamic Routing Between Capsules. Advances in Neural Information Processing Systems (NeurIPS). link ↗
Hinton, G. E., Sabour, S. & Frosst, N. (2018). Matrix Capsules with EM Routing. International Conference on Learning Representations (ICLR). link ↗

ScholarGate. (2026, June 1). Capsule Network (CapsNet). ScholarGate. https://scholargate.app/zh/deep-learning/capsule-network

Set this method beside its closest kin and read them side by side — the library lays the books on the table; the choice is yours.