Jove
Visualize
Contáctanos
JoVE
x logofacebook logolinkedin logoyoutube logo
ACERCA DE JoVE
Visión GeneralLiderazgoBlogCentro de Ayuda JoVE
AUTORES
Proceso de PublicaciónConsejo EditorialAlcance y PolíticasRevisión por ParesPreguntas FrecuentesEnviar
BIBLIOTECARIOS
TestimoniosSuscripcionesAccesoRecursosConsejo Asesor de BibliotecasPreguntas Frecuentes
INVESTIGACIÓN
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchivo
EDUCACIÓN
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualCentro de Recursos para ProfesoresSitio de Profesores
Términos y Condiciones de Uso
Política de Privacidad
Políticas

Videos de Conceptos Relacionados

Passive Filters01:27

Passive Filters

606
Passive filters are utilized to shape the frequency spectrum of signals across a diverse array of applications. These filters, using only passive elements like resistors (R), inductors (L), and capacitors (C), are capable of selectively allowing or blocking certain frequency ranges without the need for external power sources.
Low-Pass Filters
Low-pass filters are designed to transmit signals with frequencies lower than the cutoff frequency, ωc, and attenuate those above it. The cutoff...
606
Divergence and Stokes' Theorems01:06

Divergence and Stokes' Theorems

2.0K
The divergence and Stokes' theorems are a variation of Green's theorem in a higher dimension. They are also a generalization of the fundamental theorem of calculus. The divergence theorem and Stokes' theorem are in a way similar to each other; The divergence theorem relates to the dot product of a vector, while Stokes' theorem relates to the curl of a vector. Many applications in physics and engineering make use of the divergence and Stokes' theorems, enabling us to write...
2.0K
Filtration00:53

Filtration

964
Filtration is a physical separation process that involves passing a suspension through a porous medium to separate solids from fluids. During filtration, solids collect on the porous medium while liquids, also collectively known as the filtrate, pass through. The filtration medium is selected based on the filtration purpose, quantity, and nature of the precipitate. The general criteria for a suitable filtering medium are that it is inert, mechanically strong, nonabsorbent toward dissolved...
964
Gauss's Law: Planar Symmetry01:27

Gauss's Law: Planar Symmetry

8.3K
A planar symmetry of charge density is obtained when charges are uniformly spread over a large flat surface. In planar symmetry, all points in a plane parallel to the plane of charge are identical with respect to the charges. Suppose the plane of the charge distribution is the xy-plane, and the electric field at a space point P with coordinates (x, y, z) is to be determined. Since the charge density is the same at all (x, y) - coordinates in the z = 0 plane, by symmetry, the electric field at P...
8.3K
Gauss's Law: Spherical Symmetry01:26

Gauss's Law: Spherical Symmetry

7.9K
A charge distribution has spherical symmetry if the density of charge depends only on the distance from a point in space and not on the direction. In other words, if the system is rotated, it doesn't look different. For instance, if a sphere of radius R is uniformly charged with charge density ρ0, then the distribution has spherical symmetry. On the other hand, if a sphere of radius R is charged so that the top half of the sphere has a uniform charge density ρ1 and the bottom half...
7.9K
Gauss's Law: Problem-Solving01:10

Gauss's Law: Problem-Solving

2.1K
Gauss's law helps determine electric fields even though the law is not directly about electric fields but electric flux. In situations with certain symmetries (spherical, cylindrical, or planar) in the charge distribution, the electric field can be deduced based on the knowledge of the electric flux. In these systems, we can find a Gaussian surface S over which the electric field has a constant magnitude. Furthermore, suppose the electric field is parallel (or antiparallel) to the area...
2.1K

También podría leer

Artículos Relacionados

Artículos vinculados a este trabajo por autores compartidos, revista y gráfico de citas.

Ordenar por
Same author

Human learning of noninvasive brain-computer interfaces via manifold geometry.

Nature neuroscience·2026
Same author

Physical contact reveals a hidden layer of cortical architecture.

bioRxiv : the preprint server for biology·2026
Same author

RNAGenScape: Property-Guided, Optimized Generation of mRNA Sequences with Manifold Langevin Dynamics.

ArXiv·2026
Same author

Sexual dimorphism in the colonic microbiome and host's transcriptomics profiles of a murine model of multiple sclerosis.

Clinical immunology communications·2026
Same author

TxPert: using multiple knowledge graphs for prediction of transcriptomic perturbation effects.

Nature biotechnology·2026
Same author

Geometry-aware graph attention networks to explain single-cell chromatin states and gene expression with SEAGALL.

Genome biology·2026
Same journal

Generative Principal Component Regression via Variational Inference.

IEEE transactions on signal processing : a publication of the IEEE Signal Processing Society·2026
Same journal

Domain Adaptive Bootstrap Aggregating.

IEEE transactions on signal processing : a publication of the IEEE Signal Processing Society·2026
Same journal

Peak Persistence Diagrams for Shape-Based Signal Estimation.

IEEE transactions on signal processing : a publication of the IEEE Signal Processing Society·2026
Same journal

An efficient solution to Hidden Markov Models on trees with coupled branches.

IEEE transactions on signal processing : a publication of the IEEE Signal Processing Society·2025
Same journal

Large-Scale Independent Vector Analysis (IVA-G) via Coresets.

IEEE transactions on signal processing : a publication of the IEEE Signal Processing Society·2025
Same journal

Principal Component Analysis in Space Forms.

IEEE transactions on signal processing : a publication of the IEEE Signal Processing Society·2025
Ver todos los artículos relacionados

Video Experimental Relacionado

Updated: Sep 10, 2025

Optical Scatter Microscopy Based on Two-Dimensional Gabor Filters
14:58

Optical Scatter Microscopy Based on Two-Dimensional Gabor Filters

Published on: June 2, 2010

9.7K

Filtros de aprendizaje para módulos de dispersión geométrica

Alexander Tong1,2, Frederik Wenkel3,2, Dhananjay Bhaskar4

  • 1Dept. of Computer Science and Operations Research, Université de Montréal.

IEEE transactions on signal processing : a publication of the IEEE Signal Processing Society
|August 22, 2025
PubMed
Resumen
Este resumen es generado por máquina.

Introducimos un módulo de dispersión geométrica que se puede aprender (LEGS) para redes neuronales de gráficos (GNNs). LEGS mejora las GNN para capturar relaciones de gráficos de mayor alcance y reduce los parámetros del modelo, superando los métodos existentes en la clasificación de gráficos y el análisis de datos bioquímicos.

Palabras clave:
Diseminación geométricaRedes neuronales de gráficosProcesamiento de señales gráficas

Más Videos Relacionados

Scattering And Absorption of Light in Planetary Regoliths
11:34

Scattering And Absorption of Light in Planetary Regoliths

Published on: July 1, 2019

10.4K
Measuring Spatially- and Directionally-varying Light Scattering from Biological Material
11:57

Measuring Spatially- and Directionally-varying Light Scattering from Biological Material

Published on: May 20, 2013

13.6K

Videos de Experimentos Relacionados

Last Updated: Sep 10, 2025

Optical Scatter Microscopy Based on Two-Dimensional Gabor Filters
14:58

Optical Scatter Microscopy Based on Two-Dimensional Gabor Filters

Published on: June 2, 2010

9.7K
Scattering And Absorption of Light in Planetary Regoliths
11:34

Scattering And Absorption of Light in Planetary Regoliths

Published on: July 1, 2019

10.4K
Measuring Spatially- and Directionally-varying Light Scattering from Biological Material
11:57

Measuring Spatially- and Directionally-varying Light Scattering from Biological Material

Published on: May 20, 2013

13.6K

Área de la Ciencia:

  • Aprendizaje automático
  • Redes neuronales de gráficos
  • Diseminación geométrica

Sus antecedentes:

  • Las redes neuronales de gráficos (GNNs) a menudo luchan por capturar dependencias de largo alcance en los datos de gráficos.
  • Las GNN existentes con frecuencia dependen de la información del vecindario local (suavidad, similitud), lo que limita sus capacidades de aprendizaje relacional.
  • Las transformaciones de dispersión geométrica ofrecen una forma de principio para extraer características, pero carecen de adaptabilidad.

Objetivo del estudio:

  • Introducir un nuevo módulo para GNN inspirado en las transformadas de dispersión geométrica.
  • Mejorar la capacidad de las GNN para aprender relaciones gráficas de mayor alcance.
  • Desarrollar una arquitectura GNN más eficiente en cuanto a parámetros.

Principales métodos:

  • Propuso un módulo de dispersión geométrica aprendible (LEGS) basado en relajaciones de transformaciones de dispersión geométricas.
  • Integró el módulo LEGS en las arquitecturas GNN, lo que permite el ajuste adaptativo de las ondas de gráfico.
  • Se han evaluado redes basadas en LEGS en referenciales de clasificación de gráficos y exploración de datos de gráficos bioquímicos.

Principales resultados:

  • Las GNN basadas en LEGS demostraron un mejor aprendizaje de las relaciones de gráficos de mayor alcance en comparación con las GNN populares.
  • El módulo propuesto dio como resultado arquitecturas simplificadas con un número significativamente menor de parámetros aprendidos.
  • Las redes LEGS coincidieron o superaron las GNN existentes y la dispersión geométrica hecha a mano en varios conjuntos de datos, especialmente en dominios bioquímicos.

Conclusiones:

  • El módulo LEGS ofrece un enfoque potente y eficiente para mejorar las GNN para el análisis de gráficos complejos.
  • LEGS integra con éxito los beneficios de la dispersión geométrica con la adaptabilidad del aprendizaje profundo.
  • Este trabajo avanza las capacidades de GNN, particularmente para aplicaciones en dominios científicos como la bioquímica.