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

Transformation of Plane Strain01:12

Transformation of Plane Strain

470
When analyzing elongated structures like bars subjected to uniformly distributed loads, it is essential to understand the transformation of plane strain when coordinate axes are rotated. This transformation helps to assess how material deformation characteristics vary with orientation, which is crucial in materials science and structural engineering.
Under plane strain conditions, typical for members where one dimension significantly exceeds the others, deformations and resultant strains are...
470
State Space Representation01:27

State Space Representation

496
The frequency-domain technique, commonly used in analyzing and designing feedback control systems, is effective for linear, time-invariant systems. However, it falls short when dealing with nonlinear, time-varying, and multiple-input multiple-output systems. The time-domain or state-space approach addresses these limitations by utilizing state variables to construct simultaneous, first-order differential equations, known as state equations, for an nth-order system.
Consider an RLC circuit, a...
496
Transformation of Plane Stress01:18

Transformation of Plane Stress

663
Studying stress transformation is essential in understanding how stress components within a material, like a cube under plane stress, change with rotation. This change is analyzed by considering a prismatic element within the cube. As the element rotates, the stress components acting on it—both normal and shearing stresses—change in magnitude and orientation. This change is quantified using trigonometric functions of the rotation angle, relating the forces acting on the rotated element's...
663
Transformers01:26

Transformers

1.7K
A device that transforms voltages from one value to another using induction is called a transformer. A transformer consists of two separate coils, or windings, wrapped around the same soft iron core. However, they are electrically insulated from each other.
The iron core has a substantial relative permeability. Therefore, the magnetic field lines generated due to the current in one winding are almost entirely confined within the core, such that the same magnetic flux permeates each turn of both...
1.7K
¹H NMR: Interpreting Distorted and Overlapping Signals01:02

¹H NMR: Interpreting Distorted and Overlapping Signals

1.4K
Spin systems where the difference in chemical shifts of the coupled nuclei is greater than ten times J are called first-order spin systems. These nuclei are weakly coupled, and their chemical shifts and coupling constant can generally be estimated from the well-separated signals in the spectrum.
As Δν decreases and the signals move closer, the doublets appear increasingly distorted. The intensities of the inner lines increase at the cost of those of the outer lines as the signals are...
1.4K
Source Transformation01:15

Source Transformation

11.0K
Source transformation is a fundamental technique employed in circuit analysis, offering a valuable tool for simplifying complex electrical circuits. This technique involves the replacement of either a voltage source in series with a resistor by a current source in parallel with a resistor, or vice versa. The key concept here is that when the original sources are deactivated (turned off), the equivalent resistance at the circuit's end terminals remains the same.
It is essential to note that when...
11.0K

También podría leer

Artículos Relacionados

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

Ordenar por
Same author

Verifiably stable nonlinear control with reinforcement-learned diffractive optical networks.

Optics express·2026
Same author

A Spatiotemporal Perspective on Dynamical Computation in Neural Information Processing Systems.

ArXiv·2026
Same author

CellSAM: a foundation model for cell segmentation.

Nature methods·2025
Same author

Learned free-energy functionals from pair-correlation matching for dynamical density functional theory.

Physical review. E·2025
Same author

Evaluation of machine learning-assisted directed evolution across diverse combinatorial landscapes.

Cell systems·2025
Same author

A Closer Look at Benchmarking Self-supervised Pre-training with Image Classification.

International journal of computer vision·2025
Same journal

Relation DETR+: Exploring Explicit Position Relation Prior for Dense Prediction.

IEEE transactions on pattern analysis and machine intelligence·2026
Same journal

RBF++: Quantifying and Optimizing Reasoning Boundaries across Measurable and Unmeasurable Capabilities for Chain-of-Thought Reasoning.

IEEE transactions on pattern analysis and machine intelligence·2026
Same journal

CAFE: Cross-View Adaptive Fusion and Cluster Center Enhancement for Robust Multi-View Clustering.

IEEE transactions on pattern analysis and machine intelligence·2026
Same journal

DIVER: Reinforced Diffusion Breaks Imitation Bottlenecks in End-to-End Autonomous Driving.

IEEE transactions on pattern analysis and machine intelligence·2026
Same journal

Ethics-Aware Safe Reinforcement Learning for Rare-Event Risk Control in Interactive Urban Driving.

IEEE transactions on pattern analysis and machine intelligence·2026
Same journal

Learning Shape Anchors for Holistic Indoor Scene Understanding.

IEEE transactions on pattern analysis and machine intelligence·2026
Ver todos los artículos relacionados

Video Experimental Relacionado

Updated: Jan 8, 2026

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

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

721

Aprendizaje de Representaciones No Supervisado a partir de Análisis de Transformaciones Dispersas

Yue Song, T Anderson Keller, Yisong Yue

    IEEE transactions on pattern analysis and machine intelligence
    |December 22, 2025
    PubMed
    Resumen
    Este resumen es generado por máquina.

    Este estudio presenta un nuevo método para aprender representaciones desentrelazadas de datos de secuencias, factorizando transformaciones en componentes dispersos utilizando modelos de flujo de probabilidad. El enfoque logra resultados de vanguardia en aprendizaje no supervisado y equivariancia aproximada.

    Palabras clave:
    aprendizaje de representacionesaprendizaje no supervisadomodelos de flujo de probabilidadrepresentaciones desentrelazadasequivariancia aproximadaanálisis de transformacionesdatos de secuenciasinteligencia artificialaprendizaje automático

    Videos de Experimentos Relacionados

    Last Updated: Jan 8, 2026

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

    Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

    Published on: July 5, 2024

    721

    Área de la Ciencia:

    • Aprendizaje Automático
    • Inteligencia Artificial
    • Aprendizaje de Representaciones

    Sus antecedentes:

    • La literatura sobre aprendizaje de representaciones explora principios como la eficiencia de codificación, la independencia estadística, la causalidad, la controlabilidad y la simetría.
    • Los métodos existentes a menudo se centran en principios específicos para aprender representaciones de datos.

    Objetivo del estudio:

    • Proponer un nuevo método para aprender representaciones a partir de datos de secuencias.
    • Factorizar las transformaciones de variables latentes en componentes dispersos utilizando modelos de flujo de probabilidad.
    • Lograr representaciones desentrelazadas y aproximadamente equivariantes.

    Principales métodos:

    • Codificar los datos de entrada como distribuciones de activaciones latentes.
    • Transformar las activaciones latentes utilizando un modelo de flujo de probabilidad descompuesto en campos de flujo rotacional y potencial.
    • Aplicar un prior de dispersión para fomentar pocos campos activos e inferir la velocidad del flujo.
    • Entrenar el modelo de forma no supervisada utilizando un objetivo variacional.

    Principales resultados:

    • El modelo aprende representaciones desentrelazadas que combinan factores independientes y primitivas de transformación.
    • Los campos de flujo aprendidos representan primitivas de transformación independientes.
    • El enfoque logra una probabilidad de datos de vanguardia.
    • Demuestra errores de equivariancia aproximada no supervisada de vanguardia en conjuntos de datos de transformación de secuencias.

    Conclusiones:

    • El método propuesto aprende eficazmente representaciones desentrelazadas y aproximadamente equivariantes a partir de datos de secuencias.
    • La factorización de transformaciones en componentes de flujo de probabilidad dispersos es una dirección prometedora para el aprendizaje de representaciones.
    • El enfoque no supervisado ofrece una nueva forma de descubrir simetrías y transformaciones de datos subyacentes.