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...

You might also read

Related Articles

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

Sort by

Same author

Exercise, daily physical activity, and age-specific cumulative incidence of mobility decline: an 8-year cohort study of locomotive syndrome.

European review of aging and physical activity : official journal of the European Group for Research into Elderly and Physical Activity·2026

Same author

An Improved Brain-Penetrating Nanoformulation of the VIPR2 Antagonist Peptide KS-133 for Treating Cognitive Impairment in Schizophrenia.

Biological & pharmaceutical bulletin·2026

Same author

Identification of alcohol dehydrogenase (ADH) isoforms catalyzing hydroxyzine oxidation using recombinant human ADH: Serendipitous finding of potent ADH inhibition by organic solvents.

Drug metabolism and disposition: the biological fate of chemicals·2026

Same author

Cold SiO<sub>2</sub>-rich slabs reaching the CMB revealed by the seifertite phase boundary.

Scientific reports·2026

Same author

Epigenetic regulation of hyaluronan degradation and melanogenesis by Kawarayomogin I and II from Artemisia capillaris via miR-486-5p and miR-141-3p.

Molecular biology reports·2026

Same author

Domain Adaptation With Additional Features via Label-Aware and Graph-Based Fused Gromov-Wasserstein Optimal Transport.

Neural computation·2026

Same journal

Dynamic analysis and reliable mechanical optimization application of ring HNN effected with a memristive neuron.

Neural networks : the official journal of the International Neural Network Society·2026

Same journal

DAFF-Net: A detection and search method for small-scale low surface brightness galaxies.

Neural networks : the official journal of the International Neural Network Society·2026

Same journal

Quasi-synchronization for complex networks with hybrid pinning intermittent control.

Neural networks : the official journal of the International Neural Network Society·2026

Same journal

Physics-encoded convolutional neural operators for parametric PDEs: A convergence-guaranteed framework via pre-computed kernel fields.

Neural networks : the official journal of the International Neural Network Society·2026

Same journal

Exploiting audio-visual modalities in videos: Object detection via multi-stage bilateral coupling network.

Neural networks : the official journal of the International Neural Network Society·2026

Same journal

Reliability-aware modality completion with cross-modal distillation for federated learning with missing modalities.

Neural networks : the official journal of the International Neural Network Society·2026

See all related articles

Search research articles

Related Experiment Video

Updated: Jul 19, 2025

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

ATNAS: Automatic Termination for Neural Architecture Search.

Kotaro Sakamoto¹, Hideaki Ishibashi², Rei Sato³

¹The Institute of Statistical Mathematics, 10-3 Midori-cho, Tachikawa, Tokyo 190-0014, Japan.

Neural Networks : the Official Journal of the International Neural Network Society

|August 11, 2023

Summary

This summary is machine-generated.

This study introduces a principled early-stopping criterion for neural architecture search (NAS). The method reduces search costs and maintains high performance by evaluating generalization error gaps, improving one-shot NAS efficiency.

Keywords:

Deep learning Neural Architecture Search

More Related Videos

Modeling the Functional Network for Spatial Navigation in the Human Brain

Modeling the Functional Network for Spatial Navigation in the Human Brain

Published on: October 13, 2023

Anatomically Inspired Three-dimensional Micro-tissue Engineered Neural Networks for Nervous System Reconstruction, Modulation, and Modeling

Anatomically Inspired Three-dimensional Micro-tissue Engineered Neural Networks for Nervous System Reconstruction, Modulation, and Modeling

Published on: May 31, 2017

Related Experiment Videos

Last Updated: Jul 19, 2025

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

Modeling the Functional Network for Spatial Navigation in the Human Brain

Modeling the Functional Network for Spatial Navigation in the Human Brain

Published on: October 13, 2023

Anatomically Inspired Three-dimensional Micro-tissue Engineered Neural Networks for Nervous System Reconstruction, Modulation, and Modeling

Anatomically Inspired Three-dimensional Micro-tissue Engineered Neural Networks for Nervous System Reconstruction, Modulation, and Modeling

Published on: May 31, 2017

Area of Science:

Artificial Intelligence
Machine Learning
Deep Learning

Background:

Neural Architecture Search (NAS) automates neural network design.
One-shot NAS methods reduce search costs but face a cost-performance trade-off.
Differentiable Architecture Search (DARTS) is prone to overfitting, necessitating effective early-stopping strategies.

Purpose of the Study:

To propose a versatile and principled early-stopping criterion for one-shot NAS.
To reduce the high computational cost associated with NAS.
To mitigate performance degradation caused by overfitting in NAS.

Main Methods:

Developed an early-stopping criterion based on the gap between expected generalization errors of successive search steps.
Proposed an automatic, cost-free determination of the stopping threshold per epoch.
Applied the criterion to stop one-shot NAS algorithms.

Main Results:

Demonstrated the effectiveness of the proposed early-stopping method in numerical experiments.
Reduced the search cost of one-shot NAS algorithms.
Maintained high performance of acquired architectures on NAS-Bench-201 and NATS-Bench datasets.

Conclusions:

The proposed early-stopping criterion offers a principled approach to optimize NAS.
Effective cost reduction in NAS is achievable without compromising performance.
The method provides a versatile solution for improving the efficiency of one-shot NAS.