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

Survival Tree01:19

Survival Tree

369
Survival trees are a non-parametric method used in survival analysis to model the relationship between a set of covariates and the time until an event of interest occurs, often referred to as the "time-to-event" or "survival time." This method is particularly useful when dealing with censored data, where the event has not occurred for some individuals by the end of the study period, or when the exact time of the event is unknown.
 Building a Survival Tree
Constructing a...
369
Quantifying and Rejecting Outliers: The Grubbs Test01:02

Quantifying and Rejecting Outliers: The Grubbs Test

3.4K
Sometimes, a data set can have a recorded numerical observation that greatly  deviates from the rest of the data. Assuming that the data is normally distributed, a statistical method called the Grubbs test can be used to determine whether the observation is truly an outlier.  To perform a two-tailed Grubbs test, first, calculate the absolute difference between the outlier and the mean. Then, calculate the ratio between this difference and the standard deviation of the sample. This...
3.4K
Woodward–Hoffmann Selection Rules and Microscopic Reversibility01:34

Woodward–Hoffmann Selection Rules and Microscopic Reversibility

3.7K
Electrocyclic reactions, cycloadditions, and sigmatropic rearrangements are concerted pericyclic reactions that proceed via a cyclic transition state. These reactions are stereospecific and regioselective. The stereochemistry of the products depends on the symmetry characteristics of the interacting orbitals and the reaction conditions. Accordingly, pericyclic reactions are classified as either symmetry-allowed or symmetry-forbidden. Woodward and Hoffmann presented the selection criteria for...
3.7K
Generalization, Discrimination, and Extinction01:24

Generalization, Discrimination, and Extinction

1.3K
Generalization, discrimination, and extinction are key concepts in operant conditioning that influence how behaviors are learned and maintained.
Generalization occurs when a behavior reinforced in one context is performed in similar situations. For instance, a student who studies diligently for calculus and receives excellent grades might apply the same study habits to psychology and history, expecting similar results. Generalization shows how learning in one setting can influence behavior in...
1.3K

También podría leer

Artículos Relacionados

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

Ordenar por
Same author

A novel major QTL underlying grain copper concentration in common wheat (Triticum aestivum L.).

BMC genomics·2024
Same author

A unified noise and watermark removal from information bottleneck-based modeling.

Neural networks : the official journal of the International Neural Network Society·2024
Same author

RIG-1 and MDA-5 signaling pathways contribute to IFN-β production and viral replication in porcine circovirus virus type 2-infected PK-15 cells in vitro.

Veterinary microbiology·2017
Same author

Melamine negatively affects testosterone synthesis in mice.

Research in veterinary science·2016
Same author

Ovarian Toxicity in Female Rats after Oral Administration of Melamine or Melamine and Cyanuric Acid.

PloS one·2016
Same journal

Research on a Regional Availability Evaluation Model for Road-Area High-Entropy Energy Based on Synergy Factors.

Entropy (Basel, Switzerland)·2026
Same journal

Atmospheric Turbulence Channel Modeling and Performance Analysis of a CO-ZP-OFDM Coherent Optical Communication System for UAV Air-to-Ground Scenarios.

Entropy (Basel, Switzerland)·2026
Same journal

Information Geometry and Asymptotic Theory for SMML Estimators.

Entropy (Basel, Switzerland)·2026
Same journal

Correlation Entropy and Power-Law Kinetics.

Entropy (Basel, Switzerland)·2026
Same journal

Research on the Contagion of Systemic Financial Risk Under the Impact of Climate Risks-From the Perspective of Complex Networks and Machine Learning.

Entropy (Basel, Switzerland)·2026
Same journal

The Statistical-Mechanical Meaning of the Wave Function of Quantum Mechanics.

Entropy (Basel, Switzerland)·2026
Ver todos los artículos relacionados

Video Experimental Relacionado

Updated: Jan 7, 2026

Quantification of Information Encoded by Gene Expression Levels During Lifespan Modulation Under Broad-range Dietary Restriction in C. elegans
09:23

Quantification of Information Encoded by Gene Expression Levels During Lifespan Modulation Under Broad-range Dietary Restriction in C. elegans

Published on: August 16, 2017

8.5K

Poda Estructurada Explicable de BERT mediante Información Mutua

Hanjuan Huang1, Hao-Jia Song2, Qiling Zhao3

  • 1College of Mechanical and Electrical Engineering, Wuyi University, Wuyishan 354300, China.

Entropy (Basel, Switzerland)
|December 24, 2025
PubMed
Resumen
Este resumen es generado por máquina.

Desarrollamos un método no supervisado para podar eficientemente modelos BERT (Bidirectional Encoder Representations from Transformers). Esta técnica reduce el tamaño del modelo y mejora el rendimiento en dispositivos de borde sin reentrenamiento.

Palabras clave:
compresión BERTexplicableinformación mutuapoda estructurada

Videos de Experimentos Relacionados

Last Updated: Jan 7, 2026

Quantification of Information Encoded by Gene Expression Levels During Lifespan Modulation Under Broad-range Dietary Restriction in C. elegans
09:23

Quantification of Information Encoded by Gene Expression Levels During Lifespan Modulation Under Broad-range Dietary Restriction in C. elegans

Published on: August 16, 2017

8.5K

Área de la Ciencia:

  • Inteligencia Artificial
  • Procesamiento del Lenguaje Natural
  • Aprendizaje Automático

Sus antecedentes:

  • Los modelos BERT (Bidirectional Encoder Representations from Transformers) son potentes para el procesamiento del lenguaje natural (PLN) pero computacionalmente costosos para dispositivos de borde.
  • Los métodos de compresión existentes a menudo requieren un reentrenamiento extenso o datos supervisados, lo que limita su aplicabilidad.

Objetivo del estudio:

  • Introducir un esquema de poda estructurada no supervisado y sin reentrenamiento para modelos BERT.
  • Reducir el costo computacional y la huella de memoria de BERT para su implementación en dispositivos de borde.

Principales métodos:

  • Un novedoso esquema de poda guiado por información mutua (MI) utilizando entropía de orden α de Rényi.
  • Desarrollo de un estimador de MI consciente de la representación y una selección de ancho de banda del kernel basada en principios para señales de poda estables y eficientes en cuanto a muestras.
  • Aplicación de visualizaciones de IA Explicable para comprender los cambios en las características y predicciones después de la compresión.

Principales resultados:

  • El método propuesto elimina eficazmente las unidades redundantes en BERT preservando la capacidad de representación.
  • Los modelos comprimidos muestran reducciones significativas en memoria y latencia, adecuados para hardware de consumo.
  • Las evaluaciones en benchmarks demuestran una pérdida mínima de precisión, superando a las bases no supervisadas y compitiendo con los métodos supervisados.

Conclusiones:

  • El esquema de poda no supervisado y sin reentrenamiento ofrece una forma eficiente de comprimir modelos BERT.
  • Este enfoque facilita la implementación de modelos avanzados de PLN en dispositivos de borde con recursos limitados.
  • El método mantiene el rendimiento del modelo y proporciona información sobre el proceso de compresión a través de IA Explicable.