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

You might also read

Related Articles

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

Sort by
Same author

The purine-rich element-binding protein ChPur-α negatively regulates Hsc70 transcription in Crassostrea hongkongensis.

Cell stress & chaperones·2017
Same author

Improved antitumor effect of ionizing radiation in combination with rapamycin for treating nasopharyngeal carcinoma.

Oncology letters·2017
Same author

Roles of Cells from the Arterial Vessel Wall in Atherosclerosis.

Mediators of inflammation·2017
Same author

Metabolic and microbial signatures in rat hepatocellular carcinoma treated with caffeic acid and chlorogenic acid.

Scientific reports·2017
Same author

Arsenic removal in aqueous solution by a novel Fe-Mn modified biochar composite: Characterization and mechanism.

Ecotoxicology and environmental safety·2017
Same author

Antidiabetic activities of polysaccharides separated from Inonotus obliquus via the modulation of oxidative stress in mice with streptozotocin-induced diabetes.

PloS one·2017

Related Experiment Video

Updated: May 22, 2025

Demonstration of Spin-Multiplexed and Direction-Multiplexed All-Dielectric Visible Metaholograms
08:48

Demonstration of Spin-Multiplexed and Direction-Multiplexed All-Dielectric Visible Metaholograms

Published on: September 25, 2020

5.7K

Flippable multitask diffractive neural networks based on double-sided metasurfaces.

He Ren, Shuai Zhou, Yuxiang Feng

    Optics Letters
    |March 14, 2025
    PubMed
    Summary

    Flippable diffractive neural networks (F-DNNs) enable multitasking by using a double-sided diffraction layer for rapid task switching. This physical computing approach offers high speed, low power, and scalability for artificial intelligence systems.

    More Related Videos

    Demonstration of Equal-Intensity Beam Generation by Dielectric Metasurfaces
    09:33

    Demonstration of Equal-Intensity Beam Generation by Dielectric Metasurfaces

    Published on: June 7, 2019

    6.2K
    Revised and Neuroimaging-Compatible Versions of the Dual Task Screen
    07:52

    Revised and Neuroimaging-Compatible Versions of the Dual Task Screen

    Published on: October 5, 2020

    3.5K

    Related Experiment Videos

    Last Updated: May 22, 2025

    Demonstration of Spin-Multiplexed and Direction-Multiplexed All-Dielectric Visible Metaholograms
    08:48

    Demonstration of Spin-Multiplexed and Direction-Multiplexed All-Dielectric Visible Metaholograms

    Published on: September 25, 2020

    5.7K
    Demonstration of Equal-Intensity Beam Generation by Dielectric Metasurfaces
    09:33

    Demonstration of Equal-Intensity Beam Generation by Dielectric Metasurfaces

    Published on: June 7, 2019

    6.2K
    Revised and Neuroimaging-Compatible Versions of the Dual Task Screen
    07:52

    Revised and Neuroimaging-Compatible Versions of the Dual Task Screen

    Published on: October 5, 2020

    3.5K

    Area of Science:

    • Optics and Photonics
    • Artificial Intelligence
    • Physical Computing

    Background:

    • Diffractive neural networks (DNNs) offer high-speed, low-power computation but struggle with multitasking due to non-reconfigurable layers.
    • Existing methods for multitask DNNs, like layer or light source replacement, are impractical.
    • Alignment issues hinder the implementation of traditional multitask DNN architectures.

    Purpose of the Study:

    • Introduce a novel flippable diffractive neural network (F-DNN) architecture.
    • Address the limitations of conventional DNNs in performing multiple tasks efficiently.
    • Provide a scalable and practical solution for multitask physical computing.

    Main Methods:

    • Designed an integrated diffraction layer processed on both sides of a substrate.
    • Implemented a 'flipping' mechanism for rapid switching between different diffraction patterns.
    • Utilized classification-based simulations to evaluate F-DNN performance.

    Main Results:

    • The F-DNN architecture successfully enables rapid task switching through layer flipping.
    • Overcame practical alignment challenges associated with layer replacement in DNNs.
    • Simulation results demonstrated superior performance and scalability compared to traditional multitask DNNs.

    Conclusions:

    • Flippable diffractive neural networks present a viable solution for multitask DNNs.
    • This approach enhances the speed, power efficiency, and multitasking capabilities of physical AI systems.
    • F-DNNs offer a new pathway for developing advanced, versatile artificial intelligence hardware.