Capsule neural network: Difference between revisions
Created page with " Capsule network try to perform the inverse of the rendering process. See also Wikipedia: Capsule Neural Network Dynamic Routing Between Capsules (NIPS 2017) * [http://p..." |
No edit summary |
||
| Line 2: | Line 2: | ||
Capsule network try to perform the inverse of the rendering process. | Capsule network try to perform the inverse of the rendering process. | ||
See also [[Wikipedia: Capsule | See also [[Wikipedia: Capsule neural network]] | ||
Dynamic Routing Between Capsules (NIPS 2017) | Dynamic Routing Between Capsules (NIPS 2017) | ||
Latest revision as of 14:56, 29 March 2023
Capsule network try to perform the inverse of the rendering process.
See also Wikipedia: Capsule neural network
Dynamic Routing Between Capsules (NIPS 2017)
Capsule
"A capsule is a group of neurons whose activity vector represents the instantiation parameters of a specific type of entity such as an object or an object part." - Nips 2017 Paper
- Rather than a neuron outputting one value, each capsule outputs a vector
- Each capsule then predicts the next layer's output
- Done through multiplication with a learned transformation matrix
Capsule Routing
- Todo
- Add Procedure 1 from the figure
- Here \(\displaystyle b_{i,j}\) is a routing weight for link between capsules in the current and next layer