Skip to contentScholarGate
LibraryBookshelfDeskReview StudioAssistant
Sign in
On this page
IntuitionHow it worksWhen to use itStrengths & limitationsCommon pitfallsApplicationsFrequently asked🔒 Read the full methodSourcesRelated methods
Cite this pageSpotted an issue on this page? Report or suggest a fix →
Home›Deep learning›Capsule Network
Machine learning

Capsule Network

Capsule Network (CapsNet) · Also known as: Kapsül Ağı (CapsNet), CapsNet, capsule net, dynamic routing network

A Capsule Network (CapsNet) is a deep learning architecture introduced by Sara Sabour, Nicholas Frosst and Geoffrey Hinton in 2017 that organises neurons as vectors (capsules) rather than scalar activations, so that spatial hierarchy and pose (orientation) information are encoded directly. It was proposed to overcome the fragility of convolutional networks to changes in viewpoint.

ScholarGate
  1. Machine learning
  2. v1
  3. 2 Sources
  4. PUBLISHED
Cite this page →
Tools & resources
Download slides
Learn & explore

Read the full method

Members only

Sign in with a free account to read this section.

Sign in

Method map

The neighbourhood of related methods — select a node to explore.

Capsule Network
Knowledge DistillationNeural Architecture Sear…Random ForestSupport Vector MachineScore-Based Generative M…

When to use it

Suitable for classification and prediction on image or otherwise structured continuous-feature data where robustness to viewpoint and pose changes matters, with a reasonably large sample (at least about 500 observations). A GPU is recommended and the dynamic routing algorithm must be tuned. Below about 500 observations the routing cannot learn reliably and the model overfits; below roughly 200 a classical classifier such as random forest or an SVM is the better choice.

Strengths & limitations

Strengths
  • Encodes pose and spatial-hierarchy information that convolutional pooling discards, improving robustness to viewpoint changes.
  • Models explicit part-to-whole relationships through routing-by-agreement.
  • Vector capsules preserve entity properties (orientation, position) rather than collapsing them to a single activation.
Limitations
  • Requires a fairly large sample (about 500+); on smaller data the dynamic routing overfits and learns unreliably.
  • Iterative dynamic routing is computationally demanding and a GPU is recommended.
  • The routing algorithm introduces hyperparameters that must be tuned, adding training complexity.

Frequently asked

How is a capsule different from a normal neuron?

A normal neuron outputs a single scalar activation. A capsule outputs a vector whose length represents the probability that an entity is present and whose direction encodes that entity's properties, such as pose and orientation, so it carries far richer spatial information.

What is dynamic routing?

Dynamic routing-by-agreement is the algorithm that connects lower-level capsules to higher-level ones. Each lower capsule predicts the output of higher capsules, and coupling coefficients are refined iteratively so that predictions which agree reinforce each other, replacing the pooling step of a convolutional network.

How much data and compute do I need?

CapsNet needs a reasonably large dataset — at least about 500 observations — and a GPU is recommended because iterative routing is computationally demanding. Below roughly 200 observations a classical classifier such as random forest or an SVM is more appropriate.

Why use a capsule network instead of a CNN?

CapsNet was proposed specifically to address a CNN's fragility to viewpoint changes. By preserving pose and part-to-whole relationships rather than pooling them away, it can generalise better when objects appear in new orientations.

Sources

  1. Sabour, S., Frosst, N. & Hinton, G. E. (2017). Dynamic Routing Between Capsules. Advances in Neural Information Processing Systems (NeurIPS). link ↗
  2. Hinton, G. E., Sabour, S. & Frosst, N. (2018). Matrix Capsules with EM Routing. International Conference on Learning Representations (ICLR). link ↗

How to cite this page

ScholarGate. (2026, June 1). Capsule Network (CapsNet). ScholarGate. https://scholargate.app/en/deep-learning/capsule-network

Related methods

Knowledge DistillationNeural Architecture SearchRandom ForestSupport Vector Machine

Which method?

Set this method beside its closest kin and read them side by side — the library lays the books on the table; the choice is yours.

  • Knowledge DistillationDeep learning↔ compare
  • Neural Architecture SearchDeep learning↔ compare
  • Random ForestMachine learning↔ compare
  • Support Vector MachineMachine learning↔ compare
Compare side by side →

Referenced by

Score-Based Generative Model

Similar methods

Convolutional Neural NetworkCNN Image ClassificationVision TransformerGraph Attention NetworkNeural Architecture SearchResNeXtAutoencoderGraph Neural Network (Network Analysis)

Related reference concepts

Deep LearningNeural Network ArchitecturesObject Recognition and DetectionConvolutional and Sequence ModelsComputer VisionSelf-Supervised and Representation Learning

Spotted an issue on this page? Report or suggest a fix →

ScholarGate — Capsule Network (Capsule Network (CapsNet)). Retrieved 2026-07-21 from https://scholargate.app/en/deep-learning/capsule-network · Dataset: https://doi.org/10.5281/zenodo.20539026
Quick facts
Originator
Sabour, S., Frosst, N. & Hinton, G. E.
Year
2017
Type
Deep learning architecture (vector capsules with dynamic routing)
Task
Classification & prediction
MinSample
500
Related methods
Knowledge DistillationNeural Architecture SearchRandom ForestSupport Vector Machine
ScholarGate

A content-first reference library for research methods — what each one is, how it works, and where it comes from.

Open data (CC-BY)

Explore

  • Library
  • Search the library…
  • Browse by field
  • Fields
  • Journey
  • Compare
  • Which method?

Reference

  • Subjects
  • Atlas
  • Glossary
  • Methodology
  • Philosophy

Your tools

  • Bookshelf
  • Desk
  • Chat

Company

  • About
  • Pricing
  • Contact
  • Suggest a method

Entries are compiled from published sources for reference. Verifying the accuracy and suitability of any information for your own use remains your responsibility.

© 2026 ScholarGate · A research-method reference library
  • Privacy
  • Cookies
  • Terms
  • Delete account