Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Concept Videos

Vesicular Tubular Clusters01:45

Vesicular Tubular Clusters

2.7K
After budding out from the ER membrane, some COPII vesicles lose their coat and fuse with one another to form larger vesicles and interconnected tubules called vesicular tubular clusters or VTCs. These clusters constitute a compartment at the ER-Golgi interface known as ERGIC (Endoplasmic Reticulum Golgi Intermediate Compartment). The ERGIC is a mobile membrane-bound cargo transport system that sorts proteins secreted from ER and delivers them to the Golgi.
With the help of motor proteins such...
2.7K
Transport Across the Golgi01:26

Transport Across the Golgi

4.9K
While it is unclear how molecules move between adjacent Golgi cisternae, it is apparent that the molecules move from cis- cisterna, the entry face, to the trans- cisterna, the exit face. Experiments initially suggested vesicles that bud from one cisterna and fuse with the next cisterna to transport proteins between the cisternae. This vesicular transport model describes the Golgi apparatus as a relatively static structure with a unique enzyme composition in each cisterna. Molecules are...
4.9K
Rab Cascades01:25

Rab Cascades

2.9K
Rab GTPases act in a regulated cascade during membrane fusion, helping the lipid bilayers mix. The Rab family of proteins are active when bound to GTP, and inactive when bound to GDP. Hence, they act as guanine nucleotide-dependent molecular switches. Rab-GTP recognizes and binds to long or short-range tethering proteins to capture the target vesicle. These tethers coordinate with SNAREs on the vesicle and the target membrane to assemble the trans SNARE complex that locks the mixing bilayers.
2.9K
Clathrin Coated Vesicles01:12

Clathrin Coated Vesicles

7.8K
Clathrin-coated vesicles use endocytosis to transport receptors and lysosomal hydrolases from the Golgi to the lysosome in the late secretory pathway. Clathrin-mediated endocytosis was the first described endocytic process, and Clathrin-coated vesicles remain one of the most well-studied transport vesicles. The molecular machinery that generates clathrin-coated vesicles comprises over 50 proteins that precisely coordinate vesicle formation. Cell surface receptors concentrated in indented sites...
7.8K
Sequence Networks of Rotating Machines01:24

Sequence Networks of Rotating Machines

182
A Y-connected synchronous generator, grounded through a neutral impedance, is designed to produce balanced internal phase voltages with only positive-sequence components. The generator's sequence networks include a source voltage that is exclusively in the positive-sequence network. The sequence components of line-to-ground voltages at the generator terminals illustrate this configuration.
Zero-sequence current induces a voltage drop across the generator's neutral impedance and other...
182
Cluster Sampling Method01:20

Cluster Sampling Method

13.2K
Appropriate sampling methods ensure that samples are drawn without bias and accurately represent the population. Because measuring the entire population in a study is not practical, researchers use samples to represent the population of interest.
To choose a cluster sample, divide the population into clusters (groups) and then randomly select some of the clusters. All the members from these clusters are in the cluster sample. For example, if you randomly sample four departments from your...
13.2K

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Retraction of "Nanoscale Donor-Acceptor Covalent Organic Frameworks for Mitochondria-Targeted Sonodynamic Therapy and Antitumor Immunity".

Journal of the American Chemical Society·2026
Same author

Integrating Multi-View Residue Graph and Protein Language Model for Cell-Penetrating Peptide Prediction via Global-Local Graph Aggregation and Cross-Attentive Fusion.

IEEE journal of biomedical and health informatics·2026
Same author

Low-intensity pulsed ultrasound regulates the osteogenic-adipogenic differentiation balance of rat adipose-derived stem cells via the PI3K/AKT-SREBF1 signaling axis.

Stem cells translational medicine·2026
Same author

Entropy-Enabled Hierarchical Defect Architecture for Dual Enhancement of Thermoelectric and Mechanical Performance in SnTe Alloys.

Advanced materials (Deerfield Beach, Fla.)·2026
Same author

Co-Analysis of Transcriptome and Metabolome Reveals Anthocyanin Accumulation in the Female Flower Tissues of Fig Cultivar 'Silu Hongyu'.

Genes·2026
Same author

Ti<sub>3</sub>C<sub>2</sub>T<sub><i>x</i></sub> MXene Nanosheets: Bridging High-Performance Energy Storage and Comprehensive In Vivo Biocompatibility Assessment.

ACS applied materials & interfaces·2026

Related Experiment Video

Updated: Oct 23, 2025

Large Scale Energy Efficient Sensor Network Routing Using a Quantum Processor Unit
05:30

Large Scale Energy Efficient Sensor Network Routing Using a Quantum Processor Unit

Published on: September 8, 2023

852

Capsule networks with non-iterative cluster routing.

Zhihao Zhao1, Samuel Cheng1

  • 1Department of Electrical and Computer Engineering, University of Oklahoma, Norman, United States.

Neural Networks : the Official Journal of the International Neural Network Society
|August 21, 2021
PubMed
Summary
This summary is machine-generated.

This study introduces non-iterative cluster routing for capsule networks, enhancing accuracy and reducing parameters. The new method improves performance on various datasets and preserves spatial information.

Keywords:
AttentionCapsule networksData-dependentRouting procedure

More Related Videos

Separating Bacteria by Capsule Amount Using a Discontinuous Density Gradient
05:52

Separating Bacteria by Capsule Amount Using a Discontinuous Density Gradient

Published on: January 7, 2019

14.4K
Modeling the Functional Network for Spatial Navigation in the Human Brain
05:55

Modeling the Functional Network for Spatial Navigation in the Human Brain

Published on: October 13, 2023

1.3K

Related Experiment Videos

Last Updated: Oct 23, 2025

Large Scale Energy Efficient Sensor Network Routing Using a Quantum Processor Unit
05:30

Large Scale Energy Efficient Sensor Network Routing Using a Quantum Processor Unit

Published on: September 8, 2023

852
Separating Bacteria by Capsule Amount Using a Discontinuous Density Gradient
05:52

Separating Bacteria by Capsule Amount Using a Discontinuous Density Gradient

Published on: January 7, 2019

14.4K
Modeling the Functional Network for Spatial Navigation in the Human Brain
05:55

Modeling the Functional Network for Spatial Navigation in the Human Brain

Published on: October 13, 2023

1.3K

Area of Science:

  • Computer Science
  • Artificial Intelligence
  • Machine Learning

Background:

  • Capsule networks (CapsNets) utilize routing algorithms for information flow between layers.
  • Current routing methods involve capsules generating individual votes for the next layer, with inputs being a weighted sum of these votes.

Purpose of the Study:

  • To propose a novel non-iterative cluster routing algorithm for capsule networks.
  • To enhance the efficiency and performance of capsule networks in image recognition tasks.

Main Methods:

  • Introduced non-iterative cluster routing where capsules generate vote clusters instead of individual votes.
  • Next-layer capsules receive centroids from vote clusters, with weights determined by cluster variance.
  • The input to a next-layer capsule is a weighted sum of received vote cluster centroids.

Main Results:

  • Achieved state-of-the-art accuracy on Fashion-MNIST and SVHN datasets with fewer parameters.
  • Demonstrated superior accuracy on smallNORB and CIFAR-10 datasets using a moderate number of parameters.
  • Capsules produced disentangled representations and generalized well to novel viewpoints.
  • Preserved 2D spatial information, enabling accurate object reconstruction under transformations.

Conclusions:

  • Non-iterative cluster routing offers a more efficient and effective approach for capsule networks.
  • The proposed method improves accuracy, reduces model complexity, and enhances representational capabilities.
  • Capsule networks with cluster routing show strong potential for advanced image analysis and computer vision applications.