Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

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

Metabolomic and lifestyle profiles refine BMI-metabolic phenotypes in older adults.

Cell reports. Medicine·2026

Same author

VPS34 inhibition as a host-targeting anti-coronaviral strategy: Rational design of YBM with optimized pharmacokinetic parameters.

Acta pharmaceutica Sinica. B·2026

Same author

A Double-Edged Algorithm Attitude: How Appreciation and Aversion Shape Students' AI Learning Anxiety in Higher Education.

Behavioral sciences (Basel, Switzerland)·2026

Same author

Photonic Mixture-of-Experts for scalable multi-task on-chip optical neural networks.

Nature communications·2026

Same author

Fe<sub>2</sub>O<sub>3</sub> Catalysts Activating Size-Regulated Li<sub>2</sub>C<sub>2</sub>O<sub>4</sub> for Efficient Cathode Prelithiation in Li Ion Hybrid Capacitors.

ChemSusChem·2026

Same author

A novel insight into the risk of depression and anxiety onset in Parkinson's disease: the implications of GBA1 and LRRK2.

Parkinsonism & related disorders·2026

Same journal

Kat5 deficiency in alveolar type II cells licenses STAT6-driven glycolytic reprogramming and pulmonary fibrosis.

Nature communications·2026

Same journal

Continuous nonthermal slab gap formed by progressive tearing beneath Northeast Asia.

Nature communications·2026

Same journal

Zeolitic isolated protonic acid sites-mediated NH<sub>3</sub> storage for robust NO<sub>x</sub> removal.

Nature communications·2026

Same journal

Coaxially nested component with asymmetric fiber resonant cavity and separation membrane for gaseous and dissolved gases detection.

Nature communications·2026

Same journal

Near-unity charge readout signal in a nonlinear resonator without matching the sensor dissipation.

Nature communications·2026

Same journal

Prokaryotic Schlafen proteins cleave tRNAs during type III CRISPR immunity.

Nature communications·2026

See all related articles

Search research articles

Related Experiment Video

Updated: Aug 15, 2025

High-Throughput Total Internal Reflection Fluorescence and Direct Stochastic Optical Reconstruction Microscopy Using a Photonic Chip

High-Throughput Total Internal Reflection Fluorescence and Direct Stochastic Optical Reconstruction Microscopy Using a Photonic Chip

Published on: November 16, 2019

Photonic machine learning with on-chip diffractive optics.

Tingzhao Fu¹, Yubin Zang¹, Yuyao Huang¹

¹Beijing National Research Center for Information Science and Technology, Department of Electronic Engineering, Tsinghua University, Beijing, 100084, China.

Nature Communications

|January 5, 2023

Summary

This summary is machine-generated.

Researchers developed a silicon-on-insulator diffractive optical neural network (DONN) for faster AI hardware. This on-chip photonic approach achieves high accuracy in machine learning tasks with low power consumption.

More Related Videos

Measurement of Quantum Interference in a Silicon Ring Resonator Photon Source

Measurement of Quantum Interference in a Silicon Ring Resonator Photon Source

Published on: April 4, 2017

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

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

Published on: February 25, 2017

Related Experiment Videos

Last Updated: Aug 15, 2025

High-Throughput Total Internal Reflection Fluorescence and Direct Stochastic Optical Reconstruction Microscopy Using a Photonic Chip

High-Throughput Total Internal Reflection Fluorescence and Direct Stochastic Optical Reconstruction Microscopy Using a Photonic Chip

Published on: November 16, 2019

Measurement of Quantum Interference in a Silicon Ring Resonator Photon Source

Measurement of Quantum Interference in a Silicon Ring Resonator Photon Source

Published on: April 4, 2017

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

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

Published on: February 25, 2017

Area of Science:

Optics and Photonics
Artificial Intelligence
Computer Engineering

Background:

Conventional Von Neumann architecture limits high-performance information processing speeds.
Photonic approaches offer potential for accelerating complex calculations in deep learning.
Need for integrated, low-power hardware solutions for artificial intelligence.

Purpose of the Study:

To propose and demonstrate an on-chip diffractive optical neural network (DONN).
To achieve high integration and low power consumption for machine learning tasks.
To validate the performance of DONNs for classification tasks.

Main Methods:

Fabrication of 1-hidden-layer and 3-hidden-layer on-chip DONNs using a silicon-on-insulator platform.
Experimental verification of DONN performance on the Iris plants dataset classification.
Testing a 3-hidden-layer DONN for Modified National Institute of Standards and Technology (NIST) handwritten digit image classification.

Main Results:

Achieved classification accuracies of 86.7% (1-hidden-layer) and 90% (3-hidden-layer) on the Iris dataset.
Demonstrated successful classification of handwritten digits using the 3-hidden-layer DONN.
Fabricated DONNs with small footprints (0.15 mm² and 0.3 mm²).

Conclusions:

The proposed passive on-chip DONN effectively performs machine learning classification tasks.
DONNs offer a promising solution for accelerating artificial intelligence hardware.
The technology enables enhanced performance with high integration and low power consumption.