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

Fast Fourier Transform01:10

Fast Fourier Transform

271
The Fast Fourier Transform (FFT) is a computational algorithm designed to compute the Discrete Fourier Transform (DFT) efficiently. By breaking down the calculations into smaller, manageable sections, the FFT significantly reduces the computational complexity involved. Direct computation of an N-point DFT requires N2 complex multiplications, whereas the FFT algorithm needs only (N/2)log⁡2N multiplications, offering a much faster performance.
The computational efficiency of the FFT becomes...
271

You might also read

Related Articles

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

Sort by
Same author

Vortex solitons in disclination quasicrystals.

Reports on progress in physics. Physical Society (Great Britain)·2026
Same author

Dietary fiber-driven shifts in mycobiota and short-chain fatty acid landscape in porcine hindgut.

Animal microbiome·2026
Same author

Explainable deep learning framework for fecal contamination detection on chicken eggshells via portable fluorescence imaging under ambient light.

Poultry science·2026
Same author

Noncovalent Interaction-Driven Assembly Endows Casein Amyloid Fibrils with Inhibitory Activities against Starch-Hydrolyzing Enzymes.

Journal of agricultural and food chemistry·2026
Same author

Electrically controlled topological interface modes in graphene-based photonic superlattices.

Optics express·2025
Same author

Detecting <i>Escherichia coli</i> Contamination on Plant Leaf Surfaces Using UV-C Fluorescence Imaging and Deep Learning.

Plants (Basel, Switzerland)·2025

Related Experiment Video

Updated: Jun 7, 2025

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

471

Optical Fourier convolutional neural network with high efficiency in image classification.

Yan Liu, Jianwei Qin, Yanbing Liu

    Optics Express
    |November 14, 2024
    PubMed
    Summary

    Optical neural networks offer faster, more efficient computing. This study introduces a simple, accurate optical Fourier convolutional neural network for advanced image classification and low-energy applications.

    More Related Videos

    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
    Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
    04:48

    Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

    Published on: November 30, 2022

    2.7K

    Related Experiment Videos

    Last Updated: Jun 7, 2025

    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

    471
    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
    Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
    04:48

    Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

    Published on: November 30, 2022

    2.7K

    Area of Science:

    • Optics and Photonics
    • Artificial Intelligence
    • Computer Science

    Background:

    • Optical neural networks (ONNs) offer superior speed, energy efficiency, and scalability over traditional neural networks.
    • Current ONN systems often suffer from structural complexity, lengthy training times, and suboptimal accuracy.
    • Addressing these limitations is crucial for advancing optical computing.

    Purpose of the Study:

    • To introduce a novel optical neural network architecture for enhanced image classification.
    • To leverage optical coherence and diffraction for a simplified and efficient computational model.
    • To explore new avenues for high-efficiency, low-energy optical computing.

    Main Methods:

    • Development of an optical Fourier convolutional neural network (OFCNN).
    • Utilizing the diffraction of complex image light fields within the optical system.
    • Leveraging the inherent coherence properties of optical systems for computation.

    Main Results:

    • The proposed OFCNN exhibits a structurally simple design.
    • The network demonstrates fast computational speeds.
    • Significant improvements in image classification accuracy were achieved compared to existing methods.
    • The system showcases high energy efficiency and anti-interference capabilities.

    Conclusions:

    • The OFCNN presents a promising advancement in optical neural network design.
    • This research offers a pathway towards practical, high-performance optical computing solutions.
    • The findings have implications for future developments in efficient and low-power computational domains.