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 Experiment Video

Updated: Jun 6, 2025

Deep Neural Networks for Image-Based Dietary Assessment
13:19

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

9.0K

A pilot study of novel multi-filter CNN layer.

Mohamed Aboukhair1, Abdelrahim Koura1, Mohammed Kayed1

  • 1Computer Science Department, Faculty of Computers and Artificial Intelligence, Beni-Suef University, Beni Suef, Egypt.

Network (Bristol, England)
|November 29, 2024
PubMed
Summary
This summary is machine-generated.

Related Concept Videos

You might also read

Related Articles

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

Sort by
Same author

Dental Age-Group Classification from Panoramic Radiographs Using Convolutional Neural Networks.

Diagnostics (Basel, Switzerland)·2026
Same author

CNN filter sizes, effects, limitations, and challenges: An exploratory study.

Network (Bristol, England)·2025
Same author

Temporal dynamics of user activities: deep learning strategies and mathematical modeling for long-term and short-term profiling.

Scientific reports·2024
Same author

A novel and accurate deep learning-based Covid-19 diagnostic model for heart patients.

Signal, image and video processing·2023
Same author

Hierarchical cloud architecture for identifying the bite of "Egyptian cobra" based on deep learning and quantum particle swarm optimization.

Scientific reports·2023
Same author

Medical Image Classification Using Transfer Learning and Chaos Game Optimization on the Internet of Medical Things.

Computational intelligence and neuroscience·2022

This study introduces a novel multi-filter layer for convolutional neural networks (CNNs), replacing fixed 3x3 filters with varied sizes. This innovation improves CNN performance by 1-5% and enhances computational efficiency.

Area of Science:

  • Computer Science
  • Artificial Intelligence
  • Machine Learning

Background:

  • Convolutional Neural Networks (CNNs) predominantly use fixed-size filters (e.g., 3x3), limiting architectural flexibility.
  • Filter size optimization in CNNs is often treated as a black box, with limited exploration of multi-filter approaches.

Purpose of the Study:

  • To propose and evaluate a novel multi-filter layer for CNNs that utilizes filters of variant sizes.
  • To investigate the impact of multi-filter layers on CNN performance and computational efficiency.

Main Methods:

  • Developed two new CNN structures: a fixed multi-filter structure and a decreasing multi-filter structure.
  • Replaced traditional single-size filter layers with proposed multi-filter layers in CNN architectures.
Keywords:
CNNCNN StructuresClassificationNovel Layer

More Related Videos

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

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

Published on: December 15, 2023

470
Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
04:48

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

369

Related Experiment Videos

Last Updated: Jun 6, 2025

Deep Neural Networks for Image-Based Dietary Assessment
13:19

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

9.0K
Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

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

Published on: December 15, 2023

470
Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
04:48

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

369

Main Results:

  • The proposed multi-filter layer demonstrated performance improvements ranging from 1% to 5%.
  • The decreasing multi-filter structure showed enhanced learner strength and reduced computational requirements compared to the fixed structure.

Conclusions:

  • Multi-filter layers offer a promising alternative to standard fixed-size filters in CNNs.
  • The decreasing multi-filter structure presents a more efficient and effective approach for CNN design.