← 🧭 Machine Learning & Neural Networks

🧭 Capsule Networks: Preserving Spatial Hierarchies

Routing iteration: 0
Agreement:
Drag — rotate · Scroll — zoom

🧭 Capsule Networks: Preserving Spatial Hierarchies

A layered capsule network where lower-level part capsules (rendered as small oriented vectors) send weighted predictions upward to higher-level object capsules, with connecting lines that thicken and brighten over routing iterations as agreeing predictions cluster together and disagreeing ones fade out.

🔬 What It Demonstrates

A layered capsule network where lower-level part capsules (rendered as small oriented vectors) send weighted predictions upward to higher-level object capsules, with connecting lines that thicken and brighten over routing iterations as agreeing predictions cluster together and disagreeing ones fade out.

🎮 How to Use

Choose an input pose or scramble the part arrangement, then step or auto-play the routing iterations to watch coupling coefficients shift toward whichever higher-level capsule the lower-level votes agree on, and rotate the viewpoint to see how pose vectors update.

💡 Did You Know?

In Hinton's original 2017 capsule network paper, just three routing iterations were typically enough for the coupling coefficients between lower and higher-level capsules to settle into a stable agreement.