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

231
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...
231
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
Neural Circuits01:25

Neural Circuits

1.1K
Neural circuits and neuronal pools are two of the main structures found in the nervous system. Neural circuits are networks of neurons that work together to carry out a specific task or process. They consist of interconnected neurons and glial cells, which provide structural and metabolic support.
Neuronal pools are collections of nerve cells with similar functions and interact through chemical and electrical signals. These pools include both interneurons (the central neural circuit nodes that...
1.1K
Reconstruction of Signal using Interpolation01:10

Reconstruction of Signal using Interpolation

173
Signal processing techniques are essential for accurately converting continuous signals to digital formats and vice versa. When a continuous signal is sampled with a period T, the resulting sampled signal exhibits replicas of the original spectrum in the frequency domain, spaced at intervals equal to the sampling frequency. To handle this sampled signal, a zero-order hold method can be applied, which creates a piecewise constant signal by retaining each sample's value until the next...
173
Vector Representation of Complex Numbers01:16

Vector Representation of Complex Numbers

106
Complex numbers, represented in Cartesian coordinates, can also be visualized as vectors. These vectors can be expressed in polar form, emphasizing their magnitude and angle. When a complex number is input into a function, the output is another complex number, highlighting the function's zero point from which the vector representation can originate.
Consider a function defined as the product of the complex factors in the numerator divided by the product of the complex factors in the...
106

You might also read

Related Articles

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

Sort by
Same author

Learning Optimal Spectral Clustering for Functional Brain Network Generation and Classification.

IEEE journal of biomedical and health informatics·2026
Same author

Role of APOC1 and NOP16 in the diagnosis of prostate cancer.

BMC urology·2025
Same author

DDR1 Regulates Femoral Arterial Calcification in Lower-Extremity Artery Disease Through NF-Kappa B Activation.

Acta physiologica (Oxford, England)·2025
Same author

Dual-Copy VP2 expressed with CTA1-DD in transgenic Eimeria acervulina confers partial protection against infectious bursal disease virus.

Poultry science·2025
Same author

Short-term peripheral nerve stimulation or pulsed radiofrequency in elderly patients with acute herpes zoster ophthalmicus: multi-center retrospective study.

The Korean journal of pain·2025
Same author

AI learning for pediatric right ventricular assessment: development and validation across multiple centers.

NPJ digital medicine·2025
Same journal

Aggregating global-scale pixel-wise forgery cues within a graph.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

Finite-Time intermittent control for secure synchronization of Neutral-Type stochastic delayed neural networks under aperiodic DoS attacks.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

FedCAD: Cross-modal semantic alignment and distillation for cross-domain heterogeneous federated learning.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

Partial-encryption-decryption-based secure state estimation of singularly perturbed complex networks: A Paillier encryption approach.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

ResVaRe: Parameter-efficient fine-tuning for large language models via cross-layer residual vector adaptation and representation editing.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

Brain network construction and analysis for epilepsy: A methodology review.

Neural networks : the official journal of the International Neural Network Society·2026
See all related articles

Related Experiment Video

Updated: Jun 6, 2025

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

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

369

Binarized Simplicial Convolutional Neural Networks.

Yi Yan1, Ercan Engin Kuruoglu1

  • 1Tsinghua Shenzhen International Graduate School, Tsinghua University, Shenzhen, China.

Neural Networks : the Official Journal of the International Neural Network Society
|December 1, 2024
PubMed
Summary
This summary is machine-generated.

Binarized Simplicial Convolutional Neural Networks (Bi-SCNN) improve graph neural network efficiency by processing higher-order structures. This novel approach enhances computational speed and prediction accuracy for complex data, outperforming traditional methods.

Keywords:
BinarizationConvolutional Neural NetworksGraph Neural NetworksGraph learningSimplicial complex

More Related Videos

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

470
Closed-loop Neuro-robotic Experiments to Test Computational Properties of Neuronal Networks
11:18

Closed-loop Neuro-robotic Experiments to Test Computational Properties of Neuronal Networks

Published on: March 2, 2015

10.3K

Related Experiment Videos

Last Updated: Jun 6, 2025

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

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

369
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

470
Closed-loop Neuro-robotic Experiments to Test Computational Properties of Neuronal Networks
11:18

Closed-loop Neuro-robotic Experiments to Test Computational Properties of Neuronal Networks

Published on: March 2, 2015

10.3K

Area of Science:

  • Machine Learning
  • Graph Neural Networks
  • Topological Data Analysis

Background:

  • Traditional Graph Neural Networks (GNNs) are limited to node-level feature processing, neglecting complex relational data in edges and higher-order structures.
  • Simplicial Convolutional Neural Networks (SCNNs) address this by using simplicial complexes but suffer from poor time efficiency.
  • Existing methods fail to capture intricate relationships within high-dimensional graph structures effectively.

Purpose of the Study:

  • To propose a novel neural network architecture, Binarized Simplicial Convolutional Neural Networks (Bi-SCNN), for efficient processing of higher-order graph structures.
  • To enhance the time efficiency and predictive performance of Simplicial Convolutional Neural Networks.
  • To reduce model complexity and susceptibility to over-smoothing in graph representation learning.

Main Methods:

  • Introduced a Binarized Simplicial Convolutional Neural Network (Bi-SCNN) combining simplicial convolution with a weighted binary-sign forward propagation strategy.
  • Utilized the Hodge Laplacian operator within the weighted binary-sign forward propagation for efficient simplicial feature representation.
  • Implemented binarization and normalization techniques to reduce model complexity and introduce intrinsic nonlinearities.

Main Results:

  • Bi-SCNN demonstrates efficient and effective representation of simplicial features with higher-order structures, surpassing traditional graph node representations.
  • The proposed Bi-SCNN achieves reduced model complexity and shorter execution times compared to previous SCNN variants without compromising prediction performance.
  • Experiments on citation and ocean-drifter datasets confirm the efficiency and accuracy of Bi-SCNN, showing reduced susceptibility to over-smoothing.

Conclusions:

  • Bi-SCNN offers a computationally efficient and accurate method for analyzing complex graph-structured data by leveraging higher-order topological features.
  • The binarized approach effectively addresses the time efficiency limitations of existing SCNN models.
  • Bi-SCNN represents a significant advancement in graph representation learning, particularly for datasets with rich relational information.