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

Neural Circuits01:25

Neural Circuits

2.2K
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...
2.2K
Frequency-dependent Selection01:21

Frequency-dependent Selection

22.7K
When the fitness of a trait is influenced by how common it is (i.e., its frequency) relative to different traits within a population, this is referred to as frequency-dependent selection. Frequency-dependent selection may occur between species or within a single species. This type of selection can either be positive—with more common phenotypes having higher fitness—or negative, with rarer phenotypes conferring increased fitness.
22.7K

You might also read

Related Articles

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

Sort by
Same author

Electronics with switchable flexibility for 3D conforming neural interfaces.

Science advances·2026
Same author

Ferroptosis and the eye: bridging the gap between cell death and vision preservation.

Frontiers in immunology·2026
Same author

Chemical structure and P-selectin inhibition of two linear and highly regular homofucans from the brown alga Fucus vesiculosus.

Carbohydrate polymers·2026
Same author

Beyond apoptosis: platinum phototherapeutics overcome resistance by triggering diverse cell death pathways.

Chemical communications (Cambridge, England)·2026
Same author

C-ZIF7@Ag/EP Coating for Eco-Friendly Marine Protection: Near-Infrared-Responsive Self-Healing with High Antibiofouling Efficacy.

ACS applied materials & interfaces·2026
Same author

MLPH/RAB3A accelerates the differentiation of pancreatic stem cells to islet β-cells to control blood glucose in diabetic rats.

Organogenesis·2026

Related Experiment Video

Updated: Nov 23, 2025

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

814

Deep-gKnock: Nonlinear group-feature selection with deep neural networks.

Guangyu Zhu1, Tingting Zhao2

  • 1Department of Computer Science and Statistics, University of Rhode Island, United States of America.

Neural Networks : the Official Journal of the International Neural Network Society
|January 1, 2021
PubMed
Summary

This study introduces Deep-gKnock, a novel method for nonlinear group-feature selection in high-dimensional data. It effectively controls the group-wise False Discovery Rate (gFDR) and outperforms existing techniques, especially in complex scenarios.

Keywords:
Deep neural networksFalse discovery rateGroup feature selectionKnockoffs

More Related Videos

Deep Neural Networks for Image-Based Dietary Assessment
13:19

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

9.7K
Selecting Multiple Biomarker Subsets with Similarly Effective Binary Classification Performances
07:35

Selecting Multiple Biomarker Subsets with Similarly Effective Binary Classification Performances

Published on: October 11, 2018

7.8K

Related Experiment Videos

Last Updated: Nov 23, 2025

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

814
Deep Neural Networks for Image-Based Dietary Assessment
13:19

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

9.7K
Selecting Multiple Biomarker Subsets with Similarly Effective Binary Classification Performances
07:35

Selecting Multiple Biomarker Subsets with Similarly Effective Binary Classification Performances

Published on: October 11, 2018

7.8K

Area of Science:

  • Computational Biology
  • Bioinformatics
  • Machine Learning

Background:

  • High-dimensional data analysis relies heavily on feature selection.
  • Group structures in features are common in scientific data.
  • Existing group-feature selection methods are limited to linear models.

Purpose of the Study:

  • To develop a nonlinear group-feature selection method.
  • To control the group-wise False Discovery Rate (gFDR).
  • To integrate Deep Neural Networks (DNNs) with knockoff techniques.

Main Methods:

  • Designed a novel Deep Neural Network (DNN) architecture.
  • Integrated the DNN with the knockoff technique for group-feature selection.
  • Developed a method named Deep-gKnock for nonlinear group-feature selection.

Main Results:

  • Deep-gKnock achieved superior performance in power and gFDR control on synthetic data.
  • Outperformed state-of-the-art methods, especially with nonlinear relationships and high correlations.
  • Demonstrated robustness to feature distribution misspecification and network architecture changes.

Conclusions:

  • Deep-gKnock offers effective nonlinear group-feature selection with controlled gFDR.
  • The method shows significant advantages in challenging high-dimensional scenarios.
  • Achieved meaningful group-feature selection results on real-world datasets.