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

Visual System01:26

Visual System

684
Light enters the eye through the cornea, a transparent, dome-shaped surface covering the surface of the eyeball that helps to direct and focus incoming light. This light is then channeled toward the pupil, an adjustable opening whose size is controlled by the iris. The iris, a pigmented muscle, regulates the amount of light entering the eye by contracting or dilating the pupil, thereby ensuring optimal light levels for clear vision.
Once through the pupil, the light passes through the lens, a...
684
Classification of Systems-I01:26

Classification of Systems-I

294
Linearity is a system property characterized by a direct input-output relationship, combining homogeneity and additivity.
Homogeneity dictates that if an input x(t) is multiplied by a constant c, the output y(t) is multiplied by the same constant. Mathematically, this is expressed as:
294
Classification of Systems-II01:31

Classification of Systems-II

240
Continuous-time systems have continuous input and output signals, with time measured continuously. These systems are generally defined by differential or algebraic equations. For instance, in an RC circuit, the relationship between input and output voltage is expressed through a differential equation derived from Ohm's law and the capacitor relation,
240
Aggregates Classification01:29

Aggregates Classification

380
Aggregate classification is generally based on its size, petrographic characteristics, weight, and source. Size classification ranges from coarse to fine aggregates, defined by the size of the particles. Coarse aggregates are particles that do not pass through ASTM sieve No. 4, and aggregates that pass through the sieve are fine aggregates.
Petrographic classification groups aggregates based on common mineralogical characteristics. Some of the common mineral groups found in aggregates are...
380
Classification of Signals01:30

Classification of Signals

878
In signal processing, signals are classified based on various characteristics: continuous-time versus discrete-time, periodic versus aperiodic, analog versus digital, and causal versus noncausal. Each category highlights distinct properties crucial for understanding and manipulating signals.
A continuous-time signal holds a value at every instant in time, representing information seamlessly. In contrast, a discrete-time signal holds values only at specific moments, often denoted as x(n), where...
878
Force Classification01:22

Force Classification

1.6K
Forces play a crucial role in the study of physics and engineering. They are essential in describing the motion, behavior, and equilibrium of objects in the physical world. Forces can be classified based on their origin, type, and direction of action.
Contact and non-contact forces are two of the most widely used categories of forces. As the name suggests, contact forces require physical contact between two objects to act upon each other. Examples of contact forces include frictional,...
1.6K

También podría leer

Artículos Relacionados

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

Ordenar por
Same author

Plasma therapy cured a COVID-19 patient with long duration of viral shedding for 49 days: The clinical features, laboratory tests, plasma therapy, and implications for public health management.

MedComm·2021
Same author

Serum Bilirubin Is Correlated With the Progression of IgA Vasculitis With Nephritis.

Frontiers in medicine·2021
Same author

Pan-cancer analysis reveals an immunological role and prognostic potential of PXN in human cancer.

Aging·2021
Same author

The HCK/BTK inhibitor KIN-8194 is active in MYD88-driven lymphomas and overcomes mutated BTKCys481 ibrutinib resistance.

Blood·2021
Same author

Quantitative assessment of normal middle deltoid muscle elasticity at various arm abduction using ultrasound shear wave elastography.

Scientific reports·2021
Same author

Design of a core-shell catalyst: an effective strategy for suppressing side reactions in syngas for direct selective conversion to light olefins.

Chemical science·2021
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: Sep 10, 2025

Creating Objects and Object Categories for Studying Perception and Perceptual Learning
14:38

Creating Objects and Object Categories for Studying Perception and Perceptual Learning

Published on: November 2, 2012

11.9K

Selección de características basadas en la instancia para explicar clasificadores visuales

Li Tan1

  • 1Adobe, San Francisco, CA 94103, USA.

Entropy (Basel, Switzerland)
|August 28, 2025
PubMed
Resumen
Este resumen es generado por máquina.

Desarrollamos un nuevo método para explicar los clasificadores de imágenes de IA mediante la identificación de regiones de entrada causalmente influyentes. Este enfoque proporciona una visión más precisa y comprensible de las decisiones de modelo.

Palabras clave:
relación de causalidadInformación mutua condicionalInterpretabilidadFuncional de entropía de orden α de Rényi basado en la matriz

Más Videos Relacionados

Selecting Multiple Biomarker Subsets with Similarly Effective Binary Classification Performances
07:35

Selecting Multiple Biomarker Subsets with Similarly Effective Binary Classification Performances

Published on: October 11, 2018

7.6K
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 10, 2025

Creating Objects and Object Categories for Studying Perception and Perceptual Learning
14:38

Creating Objects and Object Categories for Studying Perception and Perceptual Learning

Published on: November 2, 2012

11.9K
Selecting Multiple Biomarker Subsets with Similarly Effective Binary Classification Performances
07:35

Selecting Multiple Biomarker Subsets with Similarly Effective Binary Classification Performances

Published on: October 11, 2018

7.6K
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:

  • Ciencias de la computación
  • Inteligencia artificial
  • Aprendizaje automático

Sus antecedentes:

  • Los clasificadores de imágenes de caja negra carecen de transparencia, lo que dificulta la confianza y la depuración.
  • Los métodos de interpretabilidad existentes a menudo no logran capturar las verdaderas relaciones causales.

Objetivo del estudio:

  • Proponer un nuevo marco de interpretación para los clasificadores de imágenes de caja negra.
  • Identificar las regiones de entrada con mayor influencia causal en las predicciones del modelo.

Principales métodos:

  • Integración de la selección de características de la instancia con el razonamiento causal.
  • Formalización de la influencia causal mediante el uso de un modelo causal estructural y la información mutua condicional.
  • Empleando el muestreo continuo de subconjuntos y la entropía de orden α de Rényi para la optimización.

Principales resultados:

  • El método propuesto genera explicaciones compactas, semánticamente significativas y causalmente fundamentadas.
  • Los experimentos muestran un rendimiento superior a las líneas de base existentes en la fidelidad predictiva a través de conjuntos de datos de visión.

Conclusiones:

  • Este marco ofrece un enfoque sólido para comprender las decisiones del clasificador de imágenes de caja negra.
  • El razonamiento causal proporciona una base más confiable para la interpretabilidad que las medidas tradicionales de importancia de la característica.