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

Convolution: Math, Graphics, and Discrete Signals01:24

Convolution: Math, Graphics, and Discrete Signals

229
In any LTI (Linear Time-Invariant) system, the convolution of two signals is denoted using a convolution operator, assuming all initial conditions are zero. The convolution integral can be divided into two parts: the zero-input or natural response and the zero-state or forced response, with t0 indicating the initial time.
To simplify the convolution integral, it is assumed that both the input signal and impulse response are zero for negative time values. The graphical convolution process...
229
Convolution Properties II01:17

Convolution Properties II

173
The important convolution properties include width, area, differentiation, and integration properties.
The width property indicates that if the durations of input signals are T1 and T2, then the width of the output response equals the sum of both durations, irrespective of the shapes of the two functions. For instance, convolving two rectangular pulses with durations of 2 seconds and 1 second results in a function with a width of 3 seconds.
The area property asserts that the area under the...
173
Convolution Properties I01:20

Convolution Properties I

137
Convolution computations can be simplified by utilizing their inherent properties.
The commutative property reveals that the input and the impulse response of an LTI (Linear Time-Invariant) system can be interchanged without affecting the output:
137

You might also read

Related Articles

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

Sort by
Same author

An all-optical signal processor enabling terabit-per-second real-time equalization.

Science (New York, N.Y.)·2026
Same author

Programmable Three-dimensional Photonic Neural Network Chip.

Nature communications·2026
Same author

Optical logic convolutional neural network.

Science advances·2026
Same author

Photonic edge intelligence chip for multi-modal sensing, inference and learning.

Nature communications·2025
Same author

Scaling up for end-to-end on-chip photonic neural network inference.

Light, science & applications·2025
Same author

Highly efficient photonic convolver via lossless mode-division fan-in.

Nature communications·2025

Related Experiment Video

Updated: Jun 5, 2025

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

8.0K

Redundancy-free integrated optical convolver for optical neural networks based on arrayed waveguide grating.

Shiji Zhang1, Haojun Zhou1, Bo Wu1

  • 1Wuhan National Laboratory for Optoelectronics, Huazhong University of Science and Technology, Wuhan 430074, China.

Nanophotonics (Berlin, Germany)
|December 5, 2024
PubMed
Summary

This study introduces a novel optical convolution architecture for artificial intelligence. It significantly reduces redundancy and enhances efficiency in optical neural networks (ONNs) for faster AI computations.

Keywords:
convolutionoptical computationoptical neural networksilicon photonics

More Related Videos

Optical Recording of Suprathreshold Neural Activity with Single-cell and Single-spike Resolution
08:48

Optical Recording of Suprathreshold Neural Activity with Single-cell and Single-spike Resolution

Published on: September 5, 2012

11.8K
Multimodal Volumetric Retinal Imaging by Oblique Scanning Laser Ophthalmoscopy oSLO and Optical Coherence Tomography OCT
12:22

Multimodal Volumetric Retinal Imaging by Oblique Scanning Laser Ophthalmoscopy oSLO and Optical Coherence Tomography OCT

Published on: August 4, 2018

8.5K

Related Experiment Videos

Last Updated: Jun 5, 2025

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

8.0K
Optical Recording of Suprathreshold Neural Activity with Single-cell and Single-spike Resolution
08:48

Optical Recording of Suprathreshold Neural Activity with Single-cell and Single-spike Resolution

Published on: September 5, 2012

11.8K
Multimodal Volumetric Retinal Imaging by Oblique Scanning Laser Ophthalmoscopy oSLO and Optical Coherence Tomography OCT
12:22

Multimodal Volumetric Retinal Imaging by Oblique Scanning Laser Ophthalmoscopy oSLO and Optical Coherence Tomography OCT

Published on: August 4, 2018

8.5K

Area of Science:

  • Optoelectronics
  • Artificial Intelligence
  • Computer Engineering

Background:

  • Optical neural networks (ONNs) offer high-speed and energy-efficient computation for AI.
  • Optical convolutions are crucial but current architectures suffer from input redundancy and resource waste.

Purpose of the Study:

  • To develop an integrated optical convolution architecture that eliminates redundancy.
  • To leverage arrayed waveguide grating (AWG) for efficient convolution operations.

Main Methods:

  • Designed an integrated optical convolution architecture using AWG principles.
  • Implemented a system performing M x N multiply-accumulate operations with M + N units per cycle.
  • Validated the architecture through handwritten digit recognition experiments.

Main Results:

  • Achieved 5-bit precision and 91.9% accuracy in handwritten digit recognition.
  • Demonstrated a redundancy-free architecture with low power consumption.
  • Reported high compute density of 8.53 teraOP mm⁻¹s⁻¹.

Conclusions:

  • The developed AWG-based optical convolution architecture significantly reduces redundancy and enhances efficiency.
  • The approach offers a scalable, low-power, and high-density solution for optical neural networks.
  • This work advances high-performance computing and AI applications through optimized optical hardware.