Capsule neural network: Difference between revisions

Revision as of 04:24, 5 March 2019

Revision as of 08:37, 5 March 2019

Line 7:

{{TOC limit|3}}

== storyHistory ==

In 2000 [[Geoffrey Hinton]] et. al. described an imaging system that combined segmentation and recognition into a single inference process using [[Parse tree|parse trees]]. So-called credibility networks described the joint distribution over the latent variables and over the possible parse trees. That system proved useful on the [[MNIST database|MNIST]] handwritten digit database.<ref name=":0" />

Line 14:

In Hinton's original idea one minicolumn would represent and detect one multidimensional entity.<ref>{{Citation|last=Meher Vamsi|title=Geoffrey Hinton Capsule theory|date=2017-11-15|url=https://www.youtube.com/watch?v=6S1_WqE55UQ|accessdate=2017-12-06}}</ref><ref group="note" name=":0" />

== TransformerTransformations ==

An [[Invariant (mathematics)|invariant]] is an object property that does not change as a result of some transformation. For example, the area of a circle does not change if the circle is shifted to the left.

Line 85:

==== Procedure squash ====

Because the length of the vectors represents probabilities they should be between zero (0) and one (1), and to do that a squashing function is applied:<ref name=":1"/>

:<math>\begin{array}{lcl}

1: \mathbf{procedure}~ \mathrm{squash} ( \mathbf{a} ) \\

2: \quad \triangleright \mbox{argument vector} \\

2: \quad \triangleright \mbox{return vector} \\