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: Mar 6, 2026

Fabrication and Operation of a Nano-Optical Conveyor Belt
11:10

Fabrication and Operation of a Nano-Optical Conveyor Belt

Published on: August 26, 2015

12.1K

Inverse-designed nanophotonic neural network accelerators for ultra-compact optical computing.

Joel Sved1,2, Shijie Song1,2, Liwei Li1,2

  • 1School of Electrical and Computer Engineering, The University of Sydney, Sydney, NSW, Australia.

Nature Communications
|March 4, 2026
PubMed
Summary

Related Concept Videos

You might also read

Related Articles

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

Sort by
Same journal

The BRCA1-A complex restricts replication fork reversal-dependent DNA repair in ATM deficient cells.

Nature communications·2026
Same journal

Signaling downstream of tumor-stroma interaction regulates mucinous colorectal adenocarcinoma apicobasal polarity.

Nature communications·2026
Same journal

Click-polymerized polyenamine membranes for efficient lithium extraction.

Nature communications·2026
Same journal

Joint trajectories of brain atrophy, white matter hyperintensities and cognition quantify brain maintenance.

Nature communications·2026
Same journal

Proton shuttling at electrochemical interfaces under alkaline hydrogen evolution.

Nature communications·2026
Same journal

metilene<sup>3</sup>: identifying DMRs across multiple conditions with auto-classification.

Nature communications·2026
See all related articles
This summary is machine-generated.

Researchers developed an ultra-compact photonic neural network (PNN) accelerator for energy-efficient optical computing. This inverse-designed nanophotonic device achieves high computational density and demonstrates impressive classification accuracy on benchmark datasets.

Area of Science:

  • Nanophotonics
  • Optical Computing
  • Machine Learning Hardware

Background:

  • High-density photonic integration is crucial for scaling analog optical computation.
  • Inverse design offers a pathway to novel nanophotonic devices for complex tasks.

Purpose of the Study:

  • To present an inverse-designed photonic neural network (PNN) accelerator.
  • To enable ultra-compact and energy-efficient optical computing solutions.

Main Methods:

  • Utilized a wave-based inverse-design method with 3D finite-difference time-domain simulations.
  • Exploited Maxwell's equations' linearity for spatial field reconstruction via optical coherence.
  • Treated subwavelength voxels as trainable degrees of freedom for high computational density.

More Related Videos

Fabrication of 1-D Photonic Crystal Cavity on a Nanofiber Using Femtosecond Laser-induced Ablation
13:02

Fabrication of 1-D Photonic Crystal Cavity on a Nanofiber Using Femtosecond Laser-induced Ablation

Published on: February 25, 2017

10.3K
Characterization of SiN Integrated Optical Phased Arrays on a Wafer-Scale Test Station
05:57

Characterization of SiN Integrated Optical Phased Arrays on a Wafer-Scale Test Station

Published on: April 1, 2020

8.6K

Related Experiment Videos

Last Updated: Mar 6, 2026

Fabrication and Operation of a Nano-Optical Conveyor Belt
11:10

Fabrication and Operation of a Nano-Optical Conveyor Belt

Published on: August 26, 2015

12.1K
Fabrication of 1-D Photonic Crystal Cavity on a Nanofiber Using Femtosecond Laser-induced Ablation
13:02

Fabrication of 1-D Photonic Crystal Cavity on a Nanofiber Using Femtosecond Laser-induced Ablation

Published on: February 25, 2017

10.3K
Characterization of SiN Integrated Optical Phased Arrays on a Wafer-Scale Test Station
05:57

Characterization of SiN Integrated Optical Phased Arrays on a Wafer-Scale Test Station

Published on: April 1, 2020

8.6K

Main Results:

  • Achieved a computational density of approximately 400 million parameters per mm².
  • Demonstrated on-chip MNIST and MedNIST classification with 89% and 90% accuracy, respectively.
  • Implemented PNN accelerators in footprints as small as 20 × 20 µm².

Conclusions:

  • Established a scalable and energy-efficient platform for photonic computing.
  • Bridged inverse nanophotonic design with high-performance optical information processing.
  • Paved the way for advanced analog optical computation using nanophotonic devices.