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

Targeting PHKA2 by Thymol alleviates sepsis induced cardiomyocyte pyroptosis via FOXA1/KLF4-mediated macrophage polarization.

Phytomedicine : international journal of phytotherapy and phytopharmacology·2026

Same author

Genetic Association and Clinical Relevance of TNFSF13B/BAFF and PADI4 Polymorphisms in ANCA-Associated Vasculitis: A Case-Control Study with Genetic Model Analysis in Guangxi Population.

Genes·2026

Same author

Seasonal Dynamics Without Reset: Core Microbiota Stability Across Development in a Gall-Dwelling Weevil.

Insects·2026

Same author

Prevalence and associated factors of sarcopenia in stroke inpatients: a cross-sectional study with SarQoL-assessed quality of life.

BMC neurology·2026

Same author

Depression symptom profiles and associated sociodemographic factors among perinatal women: A latent profile analysis.

Atencion primaria·2026

Same author

Chirality Engineering of BiOCl/BiOBr Hybrid Photocatalysts for Polarized-Photon-Selective Chiral Catalysis.

ACS nano·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

Same journal

IGFD-Net: Illumination-guided frequency decoupling for polarization image fusion.

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

Same journal

Multiple-Strategies dung beetle optimizer and its applications in engineering optimization and bankruptcy prediction.

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

Same journal

Aggregating global-scale pixel-wise forgery cues within a graph.

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

Same journal

Finite-Time intermittent control for secure synchronization of Neutral-Type stochastic delayed neural networks under aperiodic DoS attacks.

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

See all related articles

Search research articles

Related Experiment Video

Updated: May 5, 2026

Rewiring Neuronal Circuits: A New Method for Fast Neurite Extension and Functional Neuronal Connection

Rewiring Neuronal Circuits: A New Method for Fast Neurite Extension and Functional Neuronal Connection

Published on: June 13, 2017

On neural architecture search and hyperparameter optimization: A max-flow based approach.

Chao Xue¹, Jiaxing Li², Xiaoxing Wang³

¹School of Artificial Intelligence, Beijing University of Posts and Telecommunications, Beijing, PR China; JD Explore Academy, Beijing, PR China.

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

|May 6, 2025

Summary

This summary is machine-generated.

This study introduces novel max-flow based search algorithms for Automated Machine Learning (AutoML), enhancing Neural Architecture Search (NAS) and Hyperparameter Optimization (HPO) for efficient model development.

Keywords:

AutoML Hyperparameter optimization Neural architecture search

More Related Videos

Deep Neural Networks for Image-Based Dietary Assessment

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

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

Related Experiment Videos

Last Updated: May 5, 2026

Rewiring Neuronal Circuits: A New Method for Fast Neurite Extension and Functional Neuronal Connection

Rewiring Neuronal Circuits: A New Method for Fast Neurite Extension and Functional Neuronal Connection

Published on: June 13, 2017

Deep Neural Networks for Image-Based Dietary Assessment

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

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

Area of Science:

Artificial Intelligence
Machine Learning
Computer Science

Background:

Automated Machine Learning (AutoML) streamlines model creation for specific tasks.
Key AutoML components include Neural Architecture Search (NAS) for model design and Hyperparameter Optimization (HPO) for training.
Effective search algorithms are crucial for recommending optimal configurations based on historical data.

Purpose of the Study:

To propose a novel max-flow based search algorithm for AutoML.
To develop new AutoML strategies, MF-NAS and MF-HPO, by framing NAS and HPO as graph-based Max-Flow problems.
To graphically represent and manage the search space and strategy.

Main Methods:

Representing NAS and HPO as a Max-Flow problem on a graph.
MF-NAS utilizes parallel edges with capacities for operations like convolutions and pooling.
MF-HPO treats parallel edges as intervals within combined search spaces, with alternating updates of weights and capacities.

Main Results:

MF-NAS and MF-HPO demonstrate competitive efficacy and efficiency in experimental evaluations.
The proposed strategies effectively handle complex search spaces for NAS and HPO.
Efficiency is further improved through a semi-synchronous search mode for NAS and a warmup scheme for HPO.

Conclusions:

Max-flow based algorithms offer a novel and effective approach to AutoML.
MF-NAS and MF-HPO provide a graphical framework for optimizing model construction and training.
The proposed methods advance the field of efficient and effective Automated Machine Learning.