Search research articles

Related Concept Videos

Neural Regulation

Neural Regulation

Digestion begins with a cephalic phase that prepares the digestive system to receive food. When our brain processes visual or olfactory information about food, it triggers impulses in the cranial nerves innervating the salivary glands and stomach to prepare for food.

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...

You might also read

Related Articles

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

Sort by

Same author

Thermodynamically programmed one-pot CRISPR platform for point-of-care SNP genotyping.

Nature communications·2026

Same author

A comprehensive survey of data-driven technologies for construction solid waste recycling systems.

Waste management (New York, N.Y.)·2026

Same author

Multi-batch treatment of swine slaughterhouse wastewater by microalgal-fungal consortium system: Stability and effects on dissolved organic matter.

Environmental research·2026

Same author

Ginkgolide A enhances cardiomyocyte differentiation from pluripotent stem cells by targeting cytochrome c to attenuate intrinsic apoptosis.

The Journal of biological chemistry·2026

Same author

Targeted silencing of CLYBL with platelet-mimetic siRNA nanoparticles drives itaconate-mediated macrophage reprogramming and protects against sepsis-triggered lung cell death.

Cell death discovery·2026

Same author

New insights into effect of PBAT microplastics on latosol microbial metabolic functions.

Journal of hazardous materials·2026

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

Search research articles

Related Experiment Video

Updated: Jul 8, 2026

Closed-loop Neuro-robotic Experiments to Test Computational Properties of Neuronal Networks

Closed-loop Neuro-robotic Experiments to Test Computational Properties of Neuronal Networks

Published on: March 2, 2015

Robust Reconstructed Neural Network Based on Spectral Elastic Activation.

Zecheng Tang, Xiaolong Wu, Honggui Han

IEEE Transactions on Neural Networks and Learning Systems

|April 1, 2025

Summary

This study introduces a robust reconstructed neural network (RRNN) with spectral elastic activation (SEA) to improve pattern recognition with sparse data. The novel SEA-RRNN model demonstrates enhanced robustness and convergence for neural networks facing limited sample coverage.

More Related Videos

Statistical Modelling of Cortical Connectivity Using Non-invasive Electroencephalograms

Statistical Modelling of Cortical Connectivity Using Non-invasive Electroencephalograms

Published on: November 1, 2019

Author Spotlight: Advancing Large-Scale Neural Dynamics Through HD-MEA Technology

Author Spotlight: Advancing Large-Scale Neural Dynamics Through HD-MEA Technology

Published on: March 8, 2024

Related Experiment Videos

Last Updated: Jul 8, 2026

Closed-loop Neuro-robotic Experiments to Test Computational Properties of Neuronal Networks

Closed-loop Neuro-robotic Experiments to Test Computational Properties of Neuronal Networks

Published on: March 2, 2015

Statistical Modelling of Cortical Connectivity Using Non-invasive Electroencephalograms

Statistical Modelling of Cortical Connectivity Using Non-invasive Electroencephalograms

Published on: November 1, 2019

Author Spotlight: Advancing Large-Scale Neural Dynamics Through HD-MEA Technology

Author Spotlight: Advancing Large-Scale Neural Dynamics Through HD-MEA Technology

Published on: March 8, 2024

Area of Science:

Machine Learning
Artificial Intelligence
Neural Networks

Background:

Sparse samples present a significant challenge for neural networks (NNs), limiting their ability to form representative patterns due to restricted activation range coverage.
Existing NN architectures struggle to effectively process datasets with limited or unevenly distributed data points.

Purpose of the Study:

To develop a robust reconstructed neural network (RRNN) capable of addressing the challenges posed by sparse samples.
To introduce a novel spectral elastic activation (SEA) mechanism to enhance the pattern recognition capabilities of NNs in sparse data scenarios.

Main Methods:

A spectral elastic activation (SEA) was designed to broaden NN activation ranges by incorporating a spectral increment scaled by estimated outlier degrees.
An adaptive robust gradient descent (ARGD) algorithm was developed to optimize SEA parameters, utilizing a combination of error and correntropy loss functions tuned by outlier degrees.
Theoretical analysis was conducted to validate the convergence and robustness of the proposed SEA-RRNN model.

Main Results:

The SEA-RRNN effectively broadens activation boundaries to encompass features from sparse samples.
The ARGD algorithm successfully balances the need for a robust center and a precise boundary within the SEA-RRNN.
Experimental results confirm that SEA-RRNN significantly outperforms other NN models in terms of robustness.

Conclusions:

The proposed SEA-RRNN offers a robust solution for neural network pattern recognition with sparse data.
The SEA mechanism and ARGD algorithm contribute to improved NN performance and stability in challenging data conditions.
SEA-RRNN demonstrates superior robustness, making it a promising approach for applications with limited sample availability.