Capsule neural network: Difference between revisions

Revision as of 19:02, 25 December 2018

Revision as of 11:39, 9 January 2019

Line 1:

A '''Capsule Neural Network''' ('''CapsNet''') is a machine learning system that is a type of [[artificial neural network]] (ANN) that can be used to better model hierarchical relationships. The approach is an attempt to more closely mimic biological neural organization.<ref name=":1" />

The idea is to add structures called capsules to a [[convolutional neural network]] (CNN), and to reuse output from several of those capsules to form more stable (with respect to various perturbations) representations for higher order capsules.<ref>{{Cite journalbook|last=Hinton|first=Geoffrey E.|last2=Krizhevsky|first2=Alex|last3=Wang|first3=Sida D.|date=2011-06-14|title=Transforming Auto-Encoders|url=https://link.springer.com/chapter/10.1007/978-3-642-21735-7_6|journal=Artificial Neural Networks and Machine Learning – ICANN 2011|volume=6791|series=Lecture Notes in Computer Science|language=en|publisher=Springer, Berlin, Heidelberg|pages=44–51|doi=10.1007/978-3-642-21735-7_6|isbn=9783642217340|citeseerx=10.1.1.220.5099}}</ref> The output is a vector consisting of the [[Realization (probability)|probability of an observation]], and a [[Pose (computer vision)|pose for that observation]]. This vector is similar to what is done for example when doing&nbsp;''classification with localization''&nbsp;in CNNs.

Among other benefits, capsnets address the "Picasso problem" in image recognition: images that have all the right parts but that are not in the correct spatial relationship (e.g., in a "face", the positions of the mouth and one eye are switched). For image recognition, capsnets exploit the fact that while viewpoint changes have nonlinear effects at the pixel level, they have linear effects at the part/object level.<ref name=":16">{{cite web|url=http://www.cedar.buffalo.edu/~srihari/CSE676/9.12%20CapsuleNets.pdf|title=Capsule Nets|last=Srihari|first=Sargur|publisher=[[University of Buffalo]]|access-date=2017-12-07}}</ref> This can be compared to inverting the rendering of an object of multiple parts.<ref name=":0">{{Cite book|url=http://papers.nips.cc/paper/1710-learning-to-parse-images.pdf|title=Advances in Neural Information Processing Systems 12|last=Hinton|first=Geoffrey E|last2=Ghahramani|first2=Zoubin|last3=Teh|first3=Yee Whye|date=2000|publisher=MIT Press|editor-last=Solla|editor-first=S. A.|pages=463–469|editor-last2=Leen|editor-first2=T. K.|editor-last3=Müller|editor-first3=K.}}</ref>

Line 17:

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.

Informally, an [[Equivariant map|equivariant]] is a property that changes predictably under transformation. For example, the center of a circle moves by the same amount as the circle when shifted.<ref>{{Cite web|url=https://jhui.github.io/2017/11/14/Matrix-Capsules-with-EM-routing-Capsule-Network/|title=“UnderstandingUnderstanding Matrix capsules with EM Routing (Based on Hinton's Capsule Networks)”|website=jhui.github.io|access-date=2017-12-31}}</ref>

A nonequivariant is a property whose value does not change predictably under a transformation. For example, transforming a circle into an ellipse means that its perimeter can no longer be computed as π times the diameter.

Line 197:

* {{youtube|What's wrong with convolutional neural nets|id=rTawFwUvnLE}}

* {{Cite web|url=http://www.cedar.buffalo.edu/~srihari/CSE676|title=Deep Learning|website=www.cedar.buffalo.edu|access-date=2017-12-07}}

* {{Cite web|url=https://openreview.net/pdf?id=HJWLfGWRb|title=MATRIX CAPSULES WITH EM ROUTING|last=Anonymous authors|first=|date=November 2017|website=|archive-url=|archive-date=|dead-url=|access-date=}}

* {{Cite arxiv|last=De Brabandere|first=Bert|last2=Jia|first2=Xu|last3=Tuytelaars|first3=Tinne|last4=Van Gool|first4=Luc|date=2016-05-31|title=Dynamic Filter Networks|eprint=1605.09673|class=cs.LG}}

* {{Cite arxiv|last=Dai|first=Jifeng|last2=Qi|first2=Haozhi|last3=Xiong|first3=Yuwen|last4=Li|first4=Yi|last5=Zhang|first5=Guodong|last6=Hu|first6=Han|last7=Wei|first7=Yichen|date=2017-03-17|title=Deformable Convolutional Networks|eprint=1703.06211|class=cs.CV}}