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

LUT-based end-to-end optical communication system for constellation shaping.

Optics express·2025
Same author

Threshold plasticity of SOI-GST microring resonators.

Optics express·2023
Same author

Flexible optical fiber channel modeling based on a neural network module.

Optics letters·2023
Same author

Vector distribution measurement of PMD in optical fiber links employing a wavelength-tunable SOP-OTDR.

Applied optics·2022
Same author

Measurement of the adjustable slight roughness emulated by a spatial light modulator employing the vortex beam speckle pattern.

Applied optics·2020
Same author

Temperature characteristics of a BGO fiber-optic voltage transformer.

Applied optics·2019

Related Experiment Video

Updated: Aug 17, 2025

Shaping the Amplitude and Phase of Laser Beams by Using a Phase-only Spatial Light Modulator
08:39

Shaping the Amplitude and Phase of Laser Beams by Using a Phase-only Spatial Light Modulator

Published on: January 28, 2019

9.9K

Programmable low-power consumption all-optical nonlinear activation functions using a micro-ring resonator with

Ziling Fu, Zhi Wang, Peter Bienstman

    Optics Express
    |December 16, 2022
    PubMed
    Summary

    Researchers developed a programmable optical device for all-optical neural networks. This silicon micro-ring resonator device efficiently implements various nonlinear activation functions with low power consumption, enabling advanced neuromorphic computing.

    More Related Videos

    Rejection of Fluorescence Background in Resonance and Spontaneous Raman Microspectroscopy
    15:04

    Rejection of Fluorescence Background in Resonance and Spontaneous Raman Microspectroscopy

    Published on: May 18, 2011

    13.2K
    Fabrication and Testing of Microfluidic Optomechanical Oscillators
    09:10

    Fabrication and Testing of Microfluidic Optomechanical Oscillators

    Published on: May 29, 2014

    12.3K

    Related Experiment Videos

    Last Updated: Aug 17, 2025

    Shaping the Amplitude and Phase of Laser Beams by Using a Phase-only Spatial Light Modulator
    08:39

    Shaping the Amplitude and Phase of Laser Beams by Using a Phase-only Spatial Light Modulator

    Published on: January 28, 2019

    9.9K
    Rejection of Fluorescence Background in Resonance and Spontaneous Raman Microspectroscopy
    15:04

    Rejection of Fluorescence Background in Resonance and Spontaneous Raman Microspectroscopy

    Published on: May 18, 2011

    13.2K
    Fabrication and Testing of Microfluidic Optomechanical Oscillators
    09:10

    Fabrication and Testing of Microfluidic Optomechanical Oscillators

    Published on: May 29, 2014

    12.3K

    Area of Science:

    • Photonics and Optical Computing
    • Neuromorphic Engineering
    • Materials Science

    Background:

    • All-optical neural networks require efficient hardware implementations of nonlinear activation functions.
    • Existing methods often face limitations in programmability, loss, and power consumption.
    • Phase change materials offer promising properties for optical modulation and switching.

    Purpose of the Study:

    • To demonstrate a programmable, low-loss all-optical activation function device.
    • To implement multiple nonlinear activation functions (ReLU, ELU, Softplus, RBF) using a single device.
    • To evaluate the device's performance in neuromorphic computing tasks.

    Main Methods:

    • Design and fabrication of a silicon micro-ring resonator loaded with phase change materials.
    • Programming the device to exhibit different nonlinear activation functions for optical signals.
    • Simulation of handwritten digit image classification using the implemented activation functions.

    Main Results:

    • Successful implementation of four distinct nonlinear activation functions (ReLU, ELU, Softplus, RBF) at the same wavelength.
    • Achieved a maximum power consumption of only 1.748 nJ for switching between functions.
    • Demonstrated effective performance in handwritten digit image classification simulations.

    Conclusions:

    • The developed device serves as a versatile nonlinear unit for photonic neural networks.
    • Flexible programmability of the nonlinear transfer function optimizes performance for diverse neuromorphic tasks.
    • This approach offers a low-power, efficient solution for advancing all-optical computing.