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...

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.

Active Filters

Active Filters

Active filters are electronic circuits that use operational amplifiers (op-amps), resistors, and capacitors to filter out unwanted frequency components from a signal. A first-order low-pass active filter is designed to pass signals with a frequency lower than a certain cutoff frequency and attenuate frequencies higher than that cutoff frequency. The transfer function for a first-order low-pass active filter is:

You might also read

Related Articles

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

Sort by

Same author

A preliminary oxidation-assisted derivation strategy for biomass to N,O co-doped carbon used in multifunctional capacitor applications.

Nanoscale·2026

Same author

Multifunctional copper complex-mediated self-blocking plasmid delivery of PD-L1 for tumor chemoimmunotherapy.

Colloids and surfaces. B, Biointerfaces·2026

Same author

Constructing C-O-Mn Interface via Graphene Nanoribbons to Enable a Breakthrough in Low-Valent Manganese Oxide Aqueous Zinc-Ion Battery Cathodes.

ACS applied materials & interfaces·2026

Same author

Preparation of biodegradable poly(lactic acid)-<i>b</i>-polyamide 4 block poly(ester amide) and its electrospun fibers.

RSC advances·2026

Same author

Association Between Cardiovascular Polygenic Risk and White Matter Hyperintensities: An Observational Study From the UK Biobank.

Hypertension (Dallas, Tex. : 1979)·2026

Same author

Parental age and its influence on functional dependency and cognitive decline in older adults: a cohort analysis.

Journal of health, population, and nutrition·2026

Same journal

Hidden Data Recovery and Forecasting via Next-Generation Reservoir Computing With Multiscale Delay Selection.

IEEE transactions on neural networks and learning systems·2026

Same journal

CAFF-CIL: Causality-Aware Freedom Forgetting Approach for Class-Incremental Learning.

IEEE transactions on neural networks and learning systems·2026

Same journal

Harmonic Autoencoding Framework for Multiple Tasks in Magnetic Particle Imaging Reconstruction.

IEEE transactions on neural networks and learning systems·2026

Same journal

A Survey on Human-Centric Voice-Face Multimodal Learning.

IEEE transactions on neural networks and learning systems·2026

Same journal

Vision-Assisted Foundation Model for Solving Multitask Vehicle Routing Problems.

IEEE transactions on neural networks and learning systems·2026

Same journal

FP3O: Enabling Proximal Policy Optimization in Multiagent Cooperation With Parameter-Sharing Versatility.

IEEE transactions on neural networks and learning systems·2026

See all related articles

Search research articles

Related Experiment Video

Updated: Nov 2, 2025

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

Network Pruning Using Adaptive Exemplar Filters.

Mingbao Lin, Rongrong Ji, Shaojie Li

IEEE Transactions on Neural Networks and Learning Systems

|June 8, 2021

Summary

This summary is machine-generated.

EPruner, an adaptive network pruning method, efficiently removes redundant filters using Affinity Propagation. This approach significantly reduces computational load and parameters while improving or minimally impacting model accuracy.

More Related Videos

Production and Isolation of Axons from Sensory Neurons for Biochemical Analysis Using Porous Filters

Production and Isolation of Axons from Sensory Neurons for Biochemical Analysis Using Porous Filters

Published on: July 8, 2014

Author Spotlight: UAV Remote Sensing for Efficient Invasive Plant Biomass Estimation

Author Spotlight: UAV Remote Sensing for Efficient Invasive Plant Biomass Estimation

Published on: February 9, 2024

Related Experiment Videos

Last Updated: Nov 2, 2025

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

Production and Isolation of Axons from Sensory Neurons for Biochemical Analysis Using Porous Filters

Production and Isolation of Axons from Sensory Neurons for Biochemical Analysis Using Porous Filters

Published on: July 8, 2014

Author Spotlight: UAV Remote Sensing for Efficient Invasive Plant Biomass Estimation

Author Spotlight: UAV Remote Sensing for Efficient Invasive Plant Biomass Estimation

Published on: February 9, 2024

Area of Science:

Computer Science
Artificial Intelligence
Machine Learning

Background:

Traditional network pruning methods often rely on hand-crafted models, leading to suboptimal performance and lengthy filter selection processes.
Existing algorithms may require extensive training data to identify important filters, increasing computational complexity.

Purpose of the Study:

To introduce an innovative and efficient network pruning approach named EPruner.
To develop an automatic and simplified pruning algorithm that overcomes the limitations of existing methods.

Main Methods:

EPruner utilizes adaptive exemplar filters, inspired by face recognition techniques.
Affinity Propagation message-passing algorithm is applied to weight matrices to determine an adaptive number of exemplar filters.
The method enables CPU implementation, offering a faster alternative to GPU-based state-of-the-art (SOTA) approaches.

Main Results:

EPruner achieves significant FLOPs reduction and parameter removal on VGGNet-16 (76.34% FLOPs, 88.80% parameters) with a slight accuracy improvement on CIFAR-10.
On ResNet-152, EPruner reduces FLOPs by 65.12% and parameters by 64.18%, with a minimal top-5 accuracy loss on ILSVRC-2012.
The exemplar weights serve as a superior initialization for model fine-tuning.

Conclusions:

EPruner offers an automatic, efficient, and data-independent network pruning solution.
The method significantly accelerates pruning through fast CPU implementation.
EPruner demonstrates competitive performance in model compression and accuracy preservation.