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

Neuroplasticity

Neuroplasticity

Neuroplasticity reflects the brain's remarkable capacity to adapt and evolve, responding dynamically to learning, experiences, or injury by reorganizing its neural circuitry. This reorganization involves creating new neural connections and refining old ones through a series of biological processes that contribute to the brain's lifelong development and adaptability.

Woodward–Hoffmann Selection Rules and Microscopic Reversibility

Woodward–Hoffmann Selection Rules and Microscopic Reversibility

Electrocyclic reactions, cycloadditions, and sigmatropic rearrangements are concerted pericyclic reactions that proceed via a cyclic transition state. These reactions are stereospecific and regioselective. The stereochemistry of the products depends on the symmetry characteristics of the interacting orbitals and the reaction conditions. Accordingly, pericyclic reactions are classified as either symmetry-allowed or symmetry-forbidden. Woodward and Hoffmann presented the selection criteria for...

Survival Tree

Survival Tree

Survival trees are a non-parametric method used in survival analysis to model the relationship between a set of covariates and the time until an event of interest occurs, often referred to as the "time-to-event" or "survival time." This method is particularly useful when dealing with censored data, where the event has not occurred for some individuals by the end of the study period, or when the exact time of the event is unknown.
Building a Survival Tree
Constructing a...

You might also read

Related Articles

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

Sort by

Same author

Benchmarking fMRI Denoising Pipelines.

Human brain mapping·2026

Same author

Inhaled Nitric Oxide via High-Flow Nasal Cannula in Postrepair Congenital Heart Disease Patients With Pulmonary Arterial Hypertension Following Extubation: A Cohort Study With Propensity Score Matching.

World journal for pediatric & congenital heart surgery·2026

Same author

Application of modular surgical supply kits to preoperative preparation for thyroid surgery: a randomized controlled study.

Frontiers in surgery·2026

Same author

Benmelstobart+anlotinib: an emerging therapeutic option in the targeted-immunotherapy era.

Frontiers in oncology·2026

Same author

Development of a resveratrol nanoemulsion/carrageenan functional film for prolonging strawberry shelf life.

International journal of biological macromolecules·2026

Same author

Effects of Clinical Pharmacist-Led Medication Management on Medication Adherence and Quality of Life in Stroke Patients Undergoing Intravenous Thrombolysis.

Medical science monitor : international medical journal of experimental and clinical research·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: Apr 23, 2026

Selecting Multiple Biomarker Subsets with Similarly Effective Binary Classification Performances

Selecting Multiple Biomarker Subsets with Similarly Effective Binary Classification Performances

Published on: October 11, 2018

Neural network pruning and simultaneous feature and structure selection.

Xinyue Zhang¹, Hong Gu¹, Toby Kenney¹

¹Department of Mathematics and Statistics, Dalhousie University, Canada.

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

|April 21, 2026

Summary

This summary is machine-generated.

Neural network pruning enhances model portability and interpretability. This new method reformulates LASSO problems, significantly improving prediction and understanding compared to existing techniques.

Keywords:

Feature selection LASSO Model selection Neural network Neural network architecture

More Related Videos

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

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

Published on: December 15, 2023

Related Experiment Videos

Last Updated: Apr 23, 2026

Selecting Multiple Biomarker Subsets with Similarly Effective Binary Classification Performances

Selecting Multiple Biomarker Subsets with Similarly Effective Binary Classification Performances

Published on: October 11, 2018

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

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

Published on: December 15, 2023

Area of Science:

Artificial Intelligence
Machine Learning
Computational Neuroscience

Background:

Large neural networks offer high predictive accuracy but are computationally expensive and difficult to interpret.
Existing neural network pruning methods often result in significant loss of predictive performance.
The interpretability and portability of neural networks are crucial for practical applications.

Purpose of the Study:

To develop an effective and stable neural network pruning method that enhances both prediction accuracy and model interpretability.
To reformulate the neural-network LASSO problem into a standard weighted regression or classification problem.
To compare the proposed method against dense networks and state-of-the-art pruning techniques.

Main Methods:

A two-step pruning approach is proposed, starting with a dense network containing all possible feed-forward subnetworks.
The first step reformulates the neural-network LASSO problem as a weighted regression/classification problem with a LASSO penalty to remove redundancy.
The second step iteratively removes non-essential links to further refine the network structure.

Main Results:

The proposed pruning method demonstrated effectiveness and stability across four simulation studies for both regression and classification tasks.
The method significantly improved prediction accuracy and interpretability compared to the original dense neural network.
Performance evaluation on ten real-world datasets (five regression, five classification) showed superiority over state-of-the-art pruning methods.

Conclusions:

The proposed neural network pruning method offers a robust approach to enhance model portability and interpretability with minimal impact on predictive accuracy.
This technique provides a valuable tool for developing more efficient and understandable neural network models.
The method's superior performance on real-world data suggests its broad applicability in machine learning.