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.

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

Author Correction: Biophysical neural adaptation mechanisms enable artificial neural networks to capture dynamic retinal computation.

Nature communications·2025

Same author

Biophysical neural adaptation mechanisms enable artificial neural networks to capture dynamic retinal computation.

Nature communications·2024

Same author

Stimulus type shapes the topology of cellular functional networks in mouse visual cortex.

Nature communications·2024

Same author

Responses to Pattern-Violating Visual Stimuli Evolve Differently Over Days in Somata and Distal Apical Dendrites.

The Journal of neuroscience : the official journal of the Society for Neuroscience·2023

Same author

Stimulus-dependent functional network topology in mouse visual cortex.

bioRxiv : the preprint server for biology·2023

Same author

Responses of pyramidal cell somata and apical dendrites in mouse visual cortex over multiple days.

Scientific data·2023

Same journal

A Model-Free Reinforcement Learning Implementation of Decision Making Under Uncertainty by Sequential Sampling.

Neural computation·2026

Same journal

DROP: Distributional and Regular Optimism and Pessimism for Reinforcement Learning.

Neural computation·2026

Same journal

Hierarchical Active Inference Using Successor Representations.

Neural computation·2026

Same journal

W-Kernel and Its Principal Space for Frequentist Evaluation of Bayesian Estimators.

Neural computation·2026

Same journal

A Hidden Markov Model-Inspired Sequence Classification Method for Hyperdimensional Computing.

Neural computation·2026

Same journal

Sparse Graphical Modeling for Electrophysiological Phase-Based Connectivity Using Circular Statistics.

Neural computation·2026

See all related articles

Search research articles

Related Experiment Video

Updated: Jun 11, 2025

Utilizing In Vivo Postnatal Electroporation to Study Cerebellar Granule Neuron Morphology and Synapse Development

Utilizing In Vivo Postnatal Electroporation to Study Cerebellar Granule Neuron Morphology and Synapse Development

Published on: June 9, 2021

Fine Granularity Is Critical for Intelligent Neural Network Pruning.

Alex Heyman¹, Joel Zylberberg²

¹Department of Electrical Engineering and Computer Science, York University, Toronto, ON, CA M3J 1P3 aheyman@yorku.ca.

Neural Computation

|October 9, 2024

Summary

This summary is machine-generated.

Intelligent neural network pruning's accuracy advantage over random pruning diminishes as granularity coarsens. Fine-grained weight pruning offers the best balance of accuracy and computational cost reduction.

More Related Videos

Author Spotlight: Unveiling the Molecular Basis of Pain Perception and Neuropathic Pain

Author Spotlight: Unveiling the Molecular Basis of Pain Perception and Neuropathic Pain

Published on: August 9, 2024

Deep Neural Networks for Image-Based Dietary Assessment

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

Related Experiment Videos

Last Updated: Jun 11, 2025

Utilizing In Vivo Postnatal Electroporation to Study Cerebellar Granule Neuron Morphology and Synapse Development

Utilizing In Vivo Postnatal Electroporation to Study Cerebellar Granule Neuron Morphology and Synapse Development

Published on: June 9, 2021

Author Spotlight: Unveiling the Molecular Basis of Pain Perception and Neuropathic Pain

Author Spotlight: Unveiling the Molecular Basis of Pain Perception and Neuropathic Pain

Published on: August 9, 2024

Deep Neural Networks for Image-Based Dietary Assessment

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

Area of Science:

Artificial Intelligence
Computer Science
Machine Learning

Background:

Neural network pruning reduces computational costs but can impact accuracy.
Pruning methods vary in granularity, from individual weights (fine) to structural components (coarse).
Fine-grained pruning removes more parameters, while coarse-grained pruning better utilizes hardware optimizations.

Purpose of the Study:

To comprehensively investigate the relationship between pruning granularity and the effectiveness of intelligent pruning compared to random pruning.
To evaluate different intelligent pruning criteria across various granularities and architectures.
To identify optimal pruning strategies for balancing accuracy and computational efficiency.

Main Methods:

Compared intelligent iterative pruning with random pruning at initialization.
Evaluated multiple pruning granularities (weight, kernel, channel) on two architectures.
Tested performance on three image classification tasks, measuring accuracy and training iterations.

Main Results:

The accuracy advantage of intelligent over random pruning significantly decreases with coarser granularity.
At high pruning rates, fine-grained weight pruning maintained near-unpruned accuracy, while coarse pruning yielded minimal gains over random pruning.
For ResNet-20 on CIFAR-10, intelligent weight pruning achieved 90.0% accuracy, kernel pruning 86.5%, and channel pruning 85.5%, versus random pruning's 85.0%.

Conclusions:

Fine-grained pruning, when combined with efficient implementations, is more promising for achieving high accuracy with low computational cost.
Coarse-grained pruning offers limited benefits over random pruning in terms of accuracy preservation.
The choice of granularity critically impacts the efficacy of intelligent neural network pruning strategies.