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

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 survival tree begins...

Stability of structures

Stability of structures

In mechanical engineering, the stability of systems under various forces is critical for designing durable and efficient structures. One fundamental way to explore these concepts is by analyzing systems like two rods connected at a pivot point, O, with a torsional spring of spring constant k at the pivot point. This system is similar in appearance to a scissor jack used to change tires on a car. In this case, the arms of the linkage (equivalent to the rods in this system) are entirely vertical,...

Distribution Reliability and Automation

Distribution Reliability and Automation

Distribution reliability in electrical power systems is critical for ensuring an uninterrupted power supply to consumers at minimal cost. According to IEEE Standard Terms, reliability is the probability that a device will function without failure over a specified time period or amount of usage. For electric power distribution, this translates to maintaining continuous power supply and addressing customer concerns over power outages. Several indices, as defined by IEEE Standard 1366-2012, are...

Improving Translational Accuracy

Improving Translational Accuracy

Base complementarity between the three base pairs of mRNA codon and the tRNA anticodon is not a failsafe mechanism. Inaccuracies can range from a single mismatch to no correct base pairing at all. The free energy difference between the correct and nearly correct base pairs can be as small as 3 kcal/ mol. With complementarity being the only proofreading step, the estimated error frequency would be one wrong amino acid in every 100 amino acids incorporated. However, error frequencies observed in...

Improving Translational Accuracy

Improving Translational Accuracy

Base complementarity between the three base pairs of mRNA codon and the tRNA anticodon is not a failsafe mechanism. Inaccuracies can range from a single mismatch to no correct base pairing at all. The free energy difference between the correct and nearly correct base pairs can be as small as 3 kcal/ mol. With complementarity being the only proofreading step, the estimated error frequency would be one wrong amino acid in every 100 amino acids incorporated. However, error frequencies observed in...

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.

You might also read

Related Articles

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

Sort by

Same author

Hierarchical Cd4SiS6/SiO2 Heterostructure Nanowire Arrays.

Nanoscale research letters·2010

Same author

Differential roles of PKA and Epac on the production of cytokines in the endotoxin-stimulated primary cultured microglia.

Journal of molecular neuroscience : MN·2010

Same author

Discovery of potent, selective, and orally bioavailable 3H-spiro[isobenzofuran-1,4'-piperidine] based melanocortin subtype-4 receptor agonists.

Bioorganic & medicinal chemistry letters·2010

Same author

Evolution of the catalytic activity of Arabidopsis thaliana glutathione transferase zeta class-1 by saturation mutagenesis.

Bioscience, biotechnology, and biochemistry·2010

Same author

Preactivation-based, one-pot combinatorial synthesis of heparin-like hexasaccharides for the analysis of heparin-protein interactions.

Chemistry (Weinheim an der Bergstrasse, Germany)·2010

Same author

Optimization of privileged structures for selective and potent melanocortin subtype-4 receptor ligands.

Bioorganic & medicinal chemistry letters·2010

Search research articles

Related Experiment Videos

Robust network pruning for enhanced accuracy under perturbations via structural and distributional consistency.

Wenhui Shi¹, Jiangang Yang², Yangbin Xu²

¹Institute of Microelectronics, Chinese Academy of Sciences, No. 3 Beitucheng West Road, Chaoyang District, Beijing, 100029, Beijing, China; University of Chinese Academy of Science, Beijing, 100049, Beijing, China.

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

|May 25, 2026

Summary

We developed a new neural network pruning method that improves model robustness by selecting channels based on feature consistency. This approach enhances model resilience to perturbations while maintaining high accuracy.

Keywords:

Channel pruning Neural network compression Robustness analysis

Related Experiment Videos

Area of Science:

Computer Science
Artificial Intelligence
Machine Learning

Background:

Neural network pruning is crucial for reducing model size and computational costs.
Existing pruning methods often overlook model robustness, leading to performance degradation under adversarial or corrupted inputs.

Purpose of the Study:

To propose a novel robustness-aware pruning method that enhances model resilience.
To investigate the correlation between intermediate feature stability and robustness degradation in neural networks.

Main Methods:

A robustness-aware pruning strategy is introduced, selecting channels based on consistency between clean and perturbed inputs.
Two metrics, Structural-aware Consistency and Distributional-aware Consistency, are proposed to quantify feature stability.
A consistency-alignment fusion mechanism, SDA-Fuse, is designed to reconcile metric conflicts and ensure stable neuron selection.

Main Results:

The proposed method demonstrates a strong correlation between intermediate feature stability and robustness.
Experiments on ImageNet-C, ImageNet-v2-C, ImageNet-C¯, and ImageNet-3DCC show improved robustness.
The method achieves a favorable trade-off between clean accuracy and robustness, with only a minor drop in accuracy.

Conclusions:

Intermediate feature stability is implicitly encoded in neural representations and can be leveraged for robust pruning.
The proposed SDA-Fuse mechanism enables effective and reliable neuron selection for enhanced model robustness.
This work offers a promising direction for developing more resilient deep learning models.