Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Related Concept Videos

Neural Circuits

Neural Circuits

Neural circuits and neuronal pools are two of the main structures found in the nervous system. Neural circuits are networks of neurons that work together to carry out a specific task or process. They consist of interconnected neurons and glial cells, which provide structural and metabolic support.
Neuronal pools are collections of nerve cells with similar functions and interact through chemical and electrical signals. These pools include both interneurons (the central neural circuit nodes that...

Ligand-Gated Ion Channel Receptor: Gating Mechanism

Ligand-Gated Ion Channel Receptor: Gating Mechanism

Ligand-gated ion channels are transmembrane proteins that play a vital role in intercellular communication and functions of the nervous system. They allow the influx of ions across the membrane once the neurotransmitter binds, allowing the subsequent transmission of electrical excitation across the neurons. Other ligand-gated ion channels, like the γ-aminobutyric acid (GABA) receptor, permit anions like chloride into the cells on the binding of the GABA molecule. Their entry into the cell...

You might also read

Related Articles

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

Sort by

Same author

Association between Socioeconomic Position and Thyroid Cancer Incidence: A Population-Based Cohort Study in China.

Cancer epidemiology, biomarkers & prevention : a publication of the American Association for Cancer Research, cosponsored by the American Society of Preventive Oncology·2026

Same author

Effect of Anterior Capsule Polishing on the Capsule-IOL Complex in Patients With Normal Axial Length: A Prospective Randomized Controlled Trial.

Journal of refractive surgery (Thorofare, N.J. : 1995)·2026

Same author

Unsupervised Clustering Subtype Analysis and Prognostic Risk Model of Cuproptosis-Related Genes for Liver Cancer.

The Turkish journal of gastroenterology : the official journal of Turkish Society of Gastroenterology·2026

Same author

The relationship between autoimmune diseases and temporomandibular disorders: A study combined with the GEO database.

Medicine·2025

Same author

AHSA1 as a prognostic biomarker and potential immunotherapeutic target in HNSCC: integrative bulk RNA-seq, scRNA-seq analyses and experimental validation.

BMC cancer·2025

Same author

Rheological Optimization of 3D-Printed Cementitious Materials Using Response Surface Methodology.

Materials (Basel, Switzerland)·2025

Search research articles

Related Experiment Video

Updated: Dec 15, 2025

A Dual Task Procedure Combined with Rapid Serial Visual Presentation to Test Attentional Blink for Nontargets

A Dual Task Procedure Combined with Rapid Serial Visual Presentation to Test Attentional Blink for Nontargets

Published on: December 5, 2014

DA-CapsNet: dual attention mechanism capsule network.

Wenkai Huang¹, Fobao Zhou²

¹Center for Research On Leading Technology of Special Equipment, School of Mechanical and Electrical Engineering, Guangzhou University, Guangzhou, 510006, China. 16796796@qq.com.

Scientific Reports

|July 11, 2020

Summary

A new Dual Attention Mechanism Capsule Network (DA-CapsNet) improves accuracy and reduces training time compared to standard Capsule Networks (CapsNet). DA-CapsNet achieves 100% accuracy on MNIST in just 8 epochs, outperforming CapsNet significantly on various image datasets.

More Related Videos

Measurement of Neurophysiological Signals of Ignoring and Attending Processes in Attention Control

Measurement of Neurophysiological Signals of Ignoring and Attending Processes in Attention Control

Published on: July 5, 2015

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

Related Experiment Videos

Last Updated: Dec 15, 2025

A Dual Task Procedure Combined with Rapid Serial Visual Presentation to Test Attentional Blink for Nontargets

A Dual Task Procedure Combined with Rapid Serial Visual Presentation to Test Attentional Blink for Nontargets

Published on: December 5, 2014

Measurement of Neurophysiological Signals of Ignoring and Attending Processes in Attention Control

Measurement of Neurophysiological Signals of Ignoring and Attending Processes in Attention Control

Published on: July 5, 2015

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

Area of Science:

Computer Science
Artificial Intelligence
Machine Learning

Background:

Capsule Networks (CapsNet) are a novel neural network architecture designed to better capture hierarchical relationships in data.
CapsNets aim to form activation capsules, representing entity properties and relationships more effectively than traditional convolutional neural networks.
Existing CapsNet models face challenges in achieving optimal performance and efficiency across diverse datasets.

Purpose of the Study:

To introduce a novel Dual Attention Mechanism Capsule Network (DA-CapsNet) architecture.
To enhance the performance and efficiency of Capsule Networks through the integration of dual attention mechanisms.
To evaluate the effectiveness of DA-CapsNet against standard CapsNet on multiple benchmark image datasets.

Main Methods:

Proposed DA-CapsNet incorporates two attention layers: Conv-Attention after the convolution layer and Caps-Attention after the PrimaryCaps layer.
The model was trained and tested on several datasets including MNIST, SVHN, CIFAR10, FashionMNIST, smallNORB, and COIL-20.
Performance was evaluated based on classification accuracy and image reconstruction capabilities.

Main Results:

DA-CapsNet achieved 100% accuracy on the MNIST test set in 8 epochs, significantly faster than CapsNet's 25 epochs.
On SVHN, CIFAR10, FashionMNIST, smallNORB, and COIL-20, DA-CapsNet demonstrated accuracy improvements of 3.46%, 2.52%, 1.57%, 1.33%, and 1.16% respectively over CapsNet.
Image reconstruction results on COIL-20 indicated a more competitive performance for DA-CapsNet.

Conclusions:

The proposed DA-CapsNet architecture significantly improves classification accuracy and training efficiency compared to standard CapsNet.
The dual attention mechanism effectively enhances the feature extraction and representation capabilities of capsule networks.
DA-CapsNet presents a promising advancement in neural network design for image recognition tasks.