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

Acceleration Vectors01:30

Acceleration Vectors

7.9K
In everyday conversation, accelerating means speeding up. Acceleration is a vector in the same direction as the change in velocity, Δv, therefore the greater the acceleration, the greater the change in velocity over a given time. Since velocity is a vector, it can change in magnitude, direction, or both. Thus acceleration is a change in speed or direction, or both. For example, if a runner traveling at 10 km/h due east slows to a stop, reverses direction, and continues their run at 10 km/h...
7.9K
Fast Fourier Transform01:10

Fast Fourier Transform

197
The Fast Fourier Transform (FFT) is a computational algorithm designed to compute the Discrete Fourier Transform (DFT) efficiently. By breaking down the calculations into smaller, manageable sections, the FFT significantly reduces the computational complexity involved. Direct computation of an N-point DFT requires N2 complex multiplications, whereas the FFT algorithm needs only (N/2)log⁡2N multiplications, offering a much faster performance.
The computational efficiency of the FFT becomes...
197
Convolution: Math, Graphics, and Discrete Signals01:24

Convolution: Math, Graphics, and Discrete Signals

195
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...
195
Convolution Properties II01:17

Convolution Properties II

143
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...
143
Convolution Properties I01:20

Convolution Properties I

118
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:
118
Extraction: Advanced Methods00:56

Extraction: Advanced Methods

386
Metal ions can be separated from one another by complexation with organic ligands–the chelating agent– to form uncharged chelates. Here, the chelating agent must contain hydrophobic groups and behave as a weak acid, losing a proton to bind with the metal. Since most organic ligands used in this process are insoluble or undergo oxidation in the aqueous phase, the chelating agent is initially added to the organic phase and extracted into the aqueous phase. The metal-ligand complex is...
386

You might also read

Related Articles

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

Sort by
Same author

Microcomb-enabled parallel self- calibration optical convolution streaming processor.

Light, science & applications·2026
Same author

Quantum state revival via coherent energy redistribution.

Science advances·2026
Same author

Photonic-waveguide-enabled femtosecond dissipative solitons in mode-locked lasers.

Optics letters·2026
Same author

Multi-Soliton Microcombs Enable Ultrafast Nanometric-Precision Ranging and Photon-Level Detection.

Advanced science (Weinheim, Baden-Wurttemberg, Germany)·2026
Same author

Structured liquid-based reconfigurable all-liquid optical fibers.

Nature communications·2025
Same author

Scalable photonic reservoir computing for parallel machine learning tasks.

Nature communications·2025
Same journal

Large-scale discovery and annotation of substructure patterns in mass spectrometry profiles.

Nature communications·2026
Same journal

Salmonella SopB suppresses post-transcriptionally regulated cytokine release to reduce early tissue inflammation and delay disease progression.

Nature communications·2026
Same journal

A human-specific microRNA controls the timing of excitatory synaptogenesis.

Nature communications·2026
Same journal

An HMA-like integrated domain in the wheat tandem kinase WTK4 recognises an RNase-like pathogen effector.

Nature communications·2026
Same journal

Learning regularities in noise engages both neural predictive activity and representational changes.

Nature communications·2026
Same journal

The H3K4 methyltransferase KMT2D is an essential cofactor for GATA1 at erythroid gene enhancers.

Nature communications·2026
See all related articles

Related Experiment Video

Updated: May 7, 2025

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

426

TOPS-speed complex-valued convolutional accelerator for feature extraction and inference.

Yunping Bai1, Yifu Xu1, Shifan Chen1

  • 1State Key Laboratory of Information Photonics and Optical Communications, Beijing University of Posts and Telecommunications, Beijing, China.

Nature Communications
|January 2, 2025
PubMed
Summary
This summary is machine-generated.

Complex-valued optical neural networks leverage both amplitude and phase for advanced data recognition. This new optical accelerator achieves over 2 Tera operations per second, enabling real-time analysis of complex data like radar images.

More Related Videos

Author Spotlight: Revolutionizing Remote Surgery with Augmented Reality and Robotics for Enhanced Precision and Accessibility
07:46

Author Spotlight: Revolutionizing Remote Surgery with Augmented Reality and Robotics for Enhanced Precision and Accessibility

Published on: August 9, 2024

579
Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
04:48

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

318

Related Experiment Videos

Last Updated: May 7, 2025

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

426
Author Spotlight: Revolutionizing Remote Surgery with Augmented Reality and Robotics for Enhanced Precision and Accessibility
07:46

Author Spotlight: Revolutionizing Remote Surgery with Augmented Reality and Robotics for Enhanced Precision and Accessibility

Published on: August 9, 2024

579
Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
04:48

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

318

Area of Science:

  • Optoelectronics
  • Artificial Intelligence
  • Signal Processing

Background:

  • Conventional neural networks process only amplitude, limiting phase-sensitive data analysis.
  • Optical neuromorphic hardware offers high performance for complex computations.
  • Increasing data demands require advanced computing solutions.

Purpose of the Study:

  • To develop and demonstrate a high-speed complex-valued optical convolution accelerator.
  • To process intricate, phase-sensitive data, such as Synthetic Aperture Radar (SAR) images.
  • To advance artificial intelligence for real-time analysis of complex environments.

Main Methods:

  • Implementation of a complex-valued optical convolution accelerator.
  • Utilizing specifically designed phasors for data processing.
  • Testing performance on real-world Synthetic Aperture Radar (SAR) satellite imagery.

Main Results:

  • Achieved operational speed exceeding 2 Tera operations per second (TOPS).
  • Demonstrated effective recognition of complex-valued SAR images.
  • Obtained an experimental accuracy of 83.8% for image recognition tasks.

Conclusions:

  • The complex-valued optical accelerator facilitates crucial phase-sensitive feature extraction.
  • This technology represents a significant advancement for AI in real-time, high-dimensional data analysis.
  • Enables processing of complex and dynamic environmental data previously unachievable.