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

Survival Tree01:19

Survival Tree

160
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...
160
Downsampling01:20

Downsampling

256
When considering a sampled sequence with zero values between sampling instants, one can replace it by taking every N-th value of the sequence. At these integer multiples of N, the original and sampled sequences coincide. This process, known as decimation, involves extracting every N-th sample from a sequence, thereby creating a more efficient sequence.
The Fourier transform of the decimated sequence reveals a combination of scaled and shifted versions of the original spectrum. This...
256
Reducing Line Loss01:18

Reducing Line Loss

194
In a three-phase circuit, line loss is an indicator of energy dissipated as heat due to the resistance of transmission lines. To address this, incorporating transformers into the system—a step-up transformer at the source and a step-down transformer at the load—is a strategic solution. Two three-phase transformers are introduced to improve this.
With a step-up transformer at the source, the voltage is increased, thereby reducing the current in the transmission lines since power loss...
194

You might also read

Related Articles

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

Sort by
Same author

Effectiveness of the Crohn's Disease Exclusion Diet for the Treatment of Crohn's Disease in the Older-Adult Population: Real-World Experience.

Digestive diseases (Basel, Switzerland)·2025
Same author

Prediction of recurrent heart failure hospitalizations and mortality using the echocardiographic Killip score.

Clinical research in cardiology : official journal of the German Cardiac Society·2024
Same author

Towards a universal mechanism for successful deep learning.

Scientific reports·2024
Same author

Hebbian dreaming for small datasets.

Neural networks : the official journal of the International Neural Network Society·2024
Same author

Enhancing the accuracies by performing pooling decisions adjacent to the output layer.

Scientific reports·2023
Same author

Efficient shallow learning as an alternative to deep learning.

Scientific reports·2023
Same journal

Erratum: Low-dimensional model for adaptive networks of spiking neurons [Phys. Rev. E 111, 014422 (2025)].

Physical review. E·2026
Same journal

Disentangling the effects of many-body forces on depletion interactions.

Physical review. E·2026
Same journal

Charge transport and mode transition in dual-energy electron beam diodes.

Physical review. E·2026
Same journal

Optimization of multisite reactions in complex compartmentalized media.

Physical review. E·2026
Same journal

Origin of geometric cohesion in nonconvex granular materials: Interplay between interdigitation and rotational constraints enhancing frictional stability.

Physical review. E·2026
Same journal

Interaction of walkers with a standing Faraday wave.

Physical review. E·2026
See all related articles

Related Experiment Video

Updated: Sep 13, 2025

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
04:48

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

523

Advanced deep architecture pruning using single-filter performance.

Yarden Tzach1, Yuval Meir1, Ronit D Gross1

  • 1Bar-Ilan University, Department of Physics, Ramat-Gan 52900, Israel.

Physical Review. E
|August 1, 2025
PubMed
Summary
This summary is machine-generated.

This study introduces a novel pruning method for deep learning (DL) models, significantly reducing computational costs without sacrificing accuracy. The technique, applied filter

More Related Videos

Author Spotlight: Advancing Alzheimer's Research – Exploring Early Detection and Multi-Omics Approaches
09:47

Author Spotlight: Advancing Alzheimer's Research – Exploring Early Detection and Multi-Omics Approaches

Published on: December 15, 2023

1.3K
A Rapid Filter Insert-based 3D Culture System for Primary Prostate Cell Differentiation
09:23

A Rapid Filter Insert-based 3D Culture System for Primary Prostate Cell Differentiation

Published on: February 13, 2017

8.7K

Related Experiment Videos

Last Updated: Sep 13, 2025

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
04:48

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

523
Author Spotlight: Advancing Alzheimer's Research – Exploring Early Detection and Multi-Omics Approaches
09:47

Author Spotlight: Advancing Alzheimer's Research – Exploring Early Detection and Multi-Omics Approaches

Published on: December 15, 2023

1.3K
A Rapid Filter Insert-based 3D Culture System for Primary Prostate Cell Differentiation
09:23

A Rapid Filter Insert-based 3D Culture System for Primary Prostate Cell Differentiation

Published on: February 13, 2017

8.7K

Area of Science:

  • Artificial Intelligence
  • Machine Learning
  • Computer Science

Background:

  • Neural network pruning reduces computational complexity, energy consumption, and latency.
  • A recent statistical mechanics-inspired viewpoint explains deep learning (DL) mechanisms by analyzing single-filter performance.
  • Understanding microscopic filter behavior reveals macroscopic network properties.

Purpose of the Study:

  • To demonstrate a method for high parameter pruning in deep architectures based on understanding DL mechanisms.
  • To introduce Applied Filter's Cluster Connections (AFCC) for efficient neural network pruning.
  • To reduce the complexity of overparameterized AI tasks.

Main Methods:

  • Utilizing a statistical mechanics-inspired viewpoint to analyze single-filter performance in DL architectures.
  • Applying the Applied Filter's Cluster Connections (AFCC) technique for high quenched dilution of convolutional layers.
  • Extending the AFCC technique to fully connected layers and single-nodal performance.

Main Results:

  • Achieved high pruning of convolutional layers in VGG-11 and EfficientNet-B0 architectures on CIFAR-100 without accuracy loss.
  • AFCC demonstrated superior performance compared to other pruning techniques at the same pruning magnitude.
  • Successfully applied the technique to fully connected layers, indicating broad applicability.

Conclusions:

  • The understanding of DL mechanisms enables high parameter pruning through AFCC.
  • AFCC is an effective technique for reducing the complexity of deep learning models.
  • This approach offers a pathway to significantly decrease the computational demands of AI tasks.