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

Transformers with Off-Nominal Turns Ratios01:25

Transformers with Off-Nominal Turns Ratios

205
In scenarios involving parallel transformers with disparate ratings, developing per-unit models requires accommodating off-nominal turns ratios. This situation arises when the selected base voltages are not proportional to the transformer’s voltage ratings. Consider a transformer where the rated voltages are related by the term a. If the chosen voltage bases satisfy a relationship involving term b, term c is defined as the ratio of these bases. This ratio is then substituted into the...
205
Vision01:24

Vision

55.3K
Vision is the result of light being detected and transduced into neural signals by the retina of the eye. This information is then further analyzed and interpreted by the brain. First, light enters the front of the eye and is focused by the cornea and lens onto the retina—a thin sheet of neural tissue lining the back of the eye. Because of refraction through the convex lens of the eye, images are projected onto the retina upside-down and reversed.
55.3K
Transformers in Distribution System01:27

Transformers in Distribution System

156
Transformers in distribution systems can be broadly categorized into distribution substation transformers and other distribution transformers. They are crucial for stepping down high transmission voltages to levels suitable for distribution and end-user applications.
Distribution substation transformers come in various ratings and typically use mineral oil for insulation and cooling. To prevent moisture and air from entering the oil, some transformers use an inert gas like nitrogen to fill the...
156
Improving Translational Accuracy02:07

Improving Translational Accuracy

11.8K
Base complementarity between the three base pairs of mRNA codon and the tRNA anticodon is not a failsafe mechanism. Inaccuracies can range from a single mismatch to no correct base pairing at all. The free energy difference between the correct and nearly correct base pairs can be as small as 3 kcal/ mol. With complementarity being the only proofreading step, the estimated error frequency would be one wrong amino acid in every 100 amino acids incorporated. However, error frequencies observed in...
11.8K
Reducing Line Loss01:18

Reducing Line Loss

193
In a three-phase circuit, line loss is an indicator of energy dissipated as heat due to the resistance of transmission lines. To address this, incorporating transformers into the system—a step-up transformer at the source and a step-down transformer at the load—is a strategic solution. Two three-phase transformers are introduced to improve this.
With a step-up transformer at the source, the voltage is increased, thereby reducing the current in the transmission lines since power loss...
193
The Ideal Transformer01:26

The Ideal Transformer

878
In single-phase two-winding transformers, two windings are coiled around a magnetic core characterized by cross-sectional area A and magnetic permeability μ. A phasor current i1 enters the left winding while i2 exits the right winding, establishing the fundamental working of the transformer through electromagnetic principles.
Ampere's Law forms the basis of understanding the magnetic field within the transformer. It states that the integral of the magnetic field intensity's...
878

También podría leer

Artículos Relacionados

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

Ordenar por
Same author

Circulating Antinephrin Antibodies in Adult Chinese Patients With IgAN and Nephrotic-Range Proteinuria.

Kidney international reports·2026
Same author

Structures of the endophytic microbiota during heart rot development in <i>Abies georgei</i> var. <i>smithii</i>.

Microbiology spectrum·2026
Same author

Controlled encapsulation and droplet size prediction in two-step microfluidic double emulsions.

Lab on a chip·2026
Same author

Oncogenic KRAS Represses the Dependence Receptor UNC5C via ERK2-FOS Signaling in Non-Small Cell Lung Cancer.

The Journal of biological chemistry·2026
Same author

Time poverty and access-based consumption: Convenience gains and risk blindness.

British journal of psychology (London, England : 1953)·2026
Same author

High-specificity kilobase-level multiplex PCR enabled by graphene oxide-dendrimer-encapsulated gold nanoparticles.

Journal of materials chemistry. B·2026
Same journal

Benchmarking the Robustness of Autonomous Driving to Environmental Illusions: A Lane Perception Perspective.

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

Learning Topology-Aware Representations via Test-Time Adaptation for Anomaly Segmentation.

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

TraGraph-GS: Trajectory Graph-based Gaussian Splatting for Arbitrary Large-Scale Scene Rendering.

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

SWIFT: A Small-World Interaction Framework for Flow-Aware Trajectory Prediction in Autonomous Driving.

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

HardFlow: Hard-Constrained Sampling for Flow-Matching Models Via Trajectory Optimization.

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

Industrial Brain: Self-Evolving Neuro-Symbolic Autonomy with Causal Resilience for Cyber-Physical Systems.

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

Video Experimental Relacionado

Updated: Sep 9, 2025

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images
04:23

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images

Published on: April 21, 2023

2.0K

FRANCIA: Optimización conjunta de tokens y poda de canales estructurales para la inferencia ViT adaptativa

Ye Li, Chen Tang, Yuan Meng

    IEEE transactions on pattern analysis and machine intelligence
    |September 2, 2025
    PubMed
    Resumen
    Este resumen es generado por máquina.

    PRANCE acelera los transformadores de visión (ViT) mediante la optimización conjunta de canales y tokens por muestra. Este marco reduce la complejidad computacional y el tamaño del modelo sin sacrificar la precisión, lo que permite una implementación eficiente de ViT.

    Más Videos Relacionados

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

    Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

    Published on: July 5, 2024

    491
    Author Spotlight: Insights into Visual Cortex Research Through Wide-View fMRI Mapping
    07:11

    Author Spotlight: Insights into Visual Cortex Research Through Wide-View fMRI Mapping

    Published on: December 8, 2023

    1.9K

    Videos de Experimentos Relacionados

    Last Updated: Sep 9, 2025

    A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images
    04:23

    A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images

    Published on: April 21, 2023

    2.0K
    Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
    04:48

    Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

    Published on: July 5, 2024

    491
    Author Spotlight: Insights into Visual Cortex Research Through Wide-View fMRI Mapping
    07:11

    Author Spotlight: Insights into Visual Cortex Research Through Wide-View fMRI Mapping

    Published on: December 8, 2023

    1.9K

    Área de la Ciencia:

    • Visión por computadora
    • Inteligencia artificial
    • Aprendizaje automático

    Sus antecedentes:

    • Los Vision Transformers (ViTs) enfrentan desafíos de implementación debido al gran tamaño del modelo y la complejidad cuadrática con el número de tokens.
    • Los métodos existentes para acelerar ViTs, como la poda y la reducción de tokens, a menudo usan proporciones fijas y descuidan la optimización conjunta, lo que lleva a una pérdida de precisión.

    Objetivo del estudio:

    • Introducir PRANCE, un nuevo marco para optimizar conjuntamente los canales activados y los tokens por muestra para acelerar la inferencia ViT.
    • Para abordar los desafíos de la computación dinámica del canal y el vasto espacio de decisión en la optimización conjunta.

    Principales métodos:

    • Desarrolló una meta-red con reparto de peso para el soporte dinámico de canales en capas de autoatención de múltiples cabezas (MHSA) y percepción de múltiples capas (MLP).
    • Empleado Proximal Policy Optimization (PPO) a través de un selector ligero para administrar de manera eficiente el problema de optimización combinatoria.
    • Se introdujo un mecanismo de capacitación "Resultado para ir" que modela la inferencia ViT como un proceso de decisión de Markov para reducir el espacio de acción y el retraso de recompensa.

    Principales resultados:

    • Se ha conseguido una reducción de aproximadamente el 50% en las FLOP (operaciones de punto flotante).
    • Retenido sólo alrededor del 10% de los tokens de entrada.
    • Mantiene la precisión Top-1 sin pérdidas, demostrando ganancias de eficiencia significativas.

    Conclusiones:

    • PRANCE ofrece un enfoque unificado para acelerar las TI mediante la optimización simultánea de la arquitectura y los datos.
    • El marco aborda efectivamente la compensación entre la compresión y la precisión, lo que permite un despliegue eficiente de ViT.