Open main menu
\( \newcommand{\P}[]{\unicode{xB6}} \newcommand{\AA}[]{\unicode{x212B}} \newcommand{\empty}[]{\emptyset} \newcommand{\O}[]{\emptyset} \newcommand{\Alpha}[]{Α} \newcommand{\Beta}[]{Β} \newcommand{\Epsilon}[]{Ε} \newcommand{\Iota}[]{Ι} \newcommand{\Kappa}[]{Κ} \newcommand{\Rho}[]{Ρ} \newcommand{\Tau}[]{Τ} \newcommand{\Zeta}[]{Ζ} \newcommand{\Mu}[]{\unicode{x039C}} \newcommand{\Chi}[]{Χ} \newcommand{\Eta}[]{\unicode{x0397}} \newcommand{\Nu}[]{\unicode{x039D}} \newcommand{\Omicron}[]{\unicode{x039F}} \DeclareMathOperator{\sgn}{sgn} \def\oiint{\mathop{\vcenter{\mathchoice{\huge\unicode{x222F}\,}{\unicode{x222F}}{\unicode{x222F}}{\unicode{x222F}}}\,}\nolimits} \def\oiiint{\mathop{\vcenter{\mathchoice{\huge\unicode{x2230}\,}{\unicode{x2230}}{\unicode{x2230}}{\unicode{x2230}}}\,}\nolimits} \)

Capsule network try to perform the inverse of the rendering process.

See also Wikipedia: Capsule Neural Network

Dynamic Routing Between Capsules (NIPS 2017)


"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

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