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

Cognitive Learning01:21

Cognitive Learning

1.0K
Cognitive learning is based on purposive behavior, incidental learning, and insight learning.
E. C. Tolman's theory of purposive behavior emphasizes that much behavior is goal-directed. He argued that to understand behavior, we must look at the entire sequence of actions leading to a goal. For instance, high school students study hard, not just due to past reinforcement but also to achieve the goal of getting into a good college.
Tolman introduced the idea that behavior is influenced by...
1.0K
Observational Learning01:12

Observational Learning

824
Albert Bandura's observational learning, also known as imitation or modeling, occurs when a person observes and imitates another's behavior. It is a quicker process than operant conditioning. A well-known example is the Bobo doll study, where children who saw an adult acting aggressively towards the doll were more likely to act aggressively when left alone, compared to those who observed a nonaggressive adult. Many psychologists view observational learning as a form of latent learning...
824
Introduction to Learning01:18

Introduction to Learning

931
Learning is the process of acquiring knowledge or skills through practice or experience, leading to long-lasting behavioral changes. This acquisition occurs through interaction with the environment and requires practice or experience. For instance, mastering a skill such as surfing requires considerable practice and experience, highlighting the essential role of repeated interactions with the environment in learning.
In contrast to learned behaviors, unlearned behaviors such as crying, sexual...
931
Purposive Learning01:22

Purposive Learning

438
E. C. Tolman emphasized the purposiveness of behavior — the idea that much of our behavior is goal-directed. For instance, employees who aim for a promotion work diligently to meet their targets. Tolman argued that when classical conditioning and operant conditioning occur, the organism acquires certain expectations. In classical conditioning, a child might fear a dog because they expect it to bite. In operant conditioning, a person might consistently work overtime because they expect a...
438
Multi-input and Multi-variable systems01:22

Multi-input and Multi-variable systems

385
Cruise control systems in cars are designed as multi-input systems to maintain a driver's desired speed while compensating for external disturbances such as changes in terrain. The block diagram for a cruise control system typically includes two main inputs: the desired speed set by the driver and any external disturbances, such as the incline of the road. By adjusting the engine throttle, the system maintains the vehicle's speed as close to the desired value as possible.
In the absence of...
385
Associative Learning01:27

Associative Learning

1.2K
Associative learning is a fundamental concept in behavioral psychology, wherein a connection is established between two stimuli or events, leading to a learned response. This process is critical in understanding how behaviors are acquired and modified. Conditioning, the mechanism through which associations are formed, can be divided into two main types: classical conditioning and operant conditioning, each elucidating different aspects of associative learning.
Classical conditioning, also known...
1.2K

También podría leer

Artículos Relacionados

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

Ordenar por
Same author

Underlying Semantic Diffusion for Effective and Efficient In-Context Learning.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2026
Same author

Exploring the Stochastic Regularisation in Normalisation Layers for Semi-Supervised Learning.

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

SD<sup>2</sup>-SNN: Self-distillation and structural decomposition framework for SNNs in continual learning.

Neural networks : the official journal of the International Neural Network Society·2026
Same author

The GSK3/SHAGGY-like OsGSK3 phosphorylates and inhibits phase separation of OsFCA at Ser-43 and Ser-45 to regulate brassinosteroid signaling and rice architecture.

The New phytologist·2026
Same author

Embodied Spatial Affordance: Spatial-Aware Affordance Learning for Embodied Navigation and Manipulation.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2026
Same author

Paving the Way for Point Cloud Video Representation Learning Using a PDE Model.

IEEE transactions on pattern analysis and machine intelligence·2026

Video Experimental Relacionado

Updated: Jan 15, 2026

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness
03:14

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness

Published on: December 6, 2024

1.0K

Integración de Conocimiento Multietapa de Modelos de Visión y Lenguaje para Aprendizaje Continuo

Hongsheng Zhang, Zhong Ji, Jingren Liu

    IEEE transactions on image processing : a publication of the IEEE Signal Processing Society
    |January 13, 2026
    PubMed
    Resumen

    Los Modelos de Visión y Lenguaje (VLM) pueden mejorarse con la Integración de Conocimiento Multietapa (MulKI) para el aprendizaje continuo. MulKI mejora la adaptación a nuevos datos mientras preserva el conocimiento existente, superando las limitaciones de los métodos de destilación actuales.

    Palabras clave:
    aprendizaje continuomodelos de visión y lenguajeintegración de conocimientodestilación del conocimientointeligencia artificial

    Más Videos Relacionados

    Constructing and Visualizing Models using Mime-based Machine-learning Framework
    06:19

    Constructing and Visualizing Models using Mime-based Machine-learning Framework

    Published on: July 22, 2025

    2.3K
    Development of a Gaze-Contingent Display Framework Designed for Perceptual and Oculomotor Research with Simulated Central Vision Loss
    07:12

    Development of a Gaze-Contingent Display Framework Designed for Perceptual and Oculomotor Research with Simulated Central Vision Loss

    Published on: April 11, 2025

    874

    Videos de Experimentos Relacionados

    Last Updated: Jan 15, 2026

    Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness
    03:14

    Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness

    Published on: December 6, 2024

    1.0K
    Constructing and Visualizing Models using Mime-based Machine-learning Framework
    06:19

    Constructing and Visualizing Models using Mime-based Machine-learning Framework

    Published on: July 22, 2025

    2.3K
    Development of a Gaze-Contingent Display Framework Designed for Perceptual and Oculomotor Research with Simulated Central Vision Loss
    07:12

    Development of a Gaze-Contingent Display Framework Designed for Perceptual and Oculomotor Research with Simulated Central Vision Loss

    Published on: April 11, 2025

    874

    Área de la Ciencia:

    • Inteligencia Artificial
    • Visión por Computadora
    • Aprendizaje Automático

    Sus antecedentes:

    • Los Modelos de Visión y Lenguaje (VLM) se destacan en tareas de cero disparos pero luchan con datos especializados no vistos.
    • El aprendizaje continuo (CL) tiene como objetivo adaptar los VLM a nuevos datos sin reentrenamiento, pero enfrenta problemas de olvido catastrófico y generalización.
    • Los métodos de destilación existentes para CL en VLM están limitados por paradigmas de un solo profesor y el uso inadecuado de datos multimodales, lo que aumenta la sobrecarga.

    Objetivo del estudio:

    • Abordar las limitaciones en el aprendizaje continuo basado en destilación actual para VLMs.
    • Proponer una nueva red, Integración de Conocimiento Multietapa (MulKI), inspirada en la Teoría de Integración de Conocimiento (KIT).
    • Mejorar la adaptación de VLM a las distribuciones de datos en evolución mientras se preservan las capacidades de cero disparos.

    Principales métodos:

    • Desarrolló la red de Integración de Conocimiento Multietapa (MulKI), emulando el aprendizaje humano a través de cuatro etapas: Obtención, Adición, Distinción y Establecimiento de Conexiones.
    • Utilizó prototipos para la alineación intermodal y construyó relaciones inter e intramodales finas.
    • Distinguió y reponderó adaptativamente el conocimiento de dos modelos profesores, integrando el conocimiento precedente y nuevo a través de las tareas.

    Principales resultados:

    • MulKI demostró mejoras significativas en el mantenimiento de las capacidades de cero disparos durante el aprendizaje continuo.
    • El método apoya eficazmente la adaptación en diversas tareas posteriores.
    • MulKI mitiga los desafíos de olvido catastrófico y olvido de generalización inherentes a CL.

    Conclusiones:

    • La red propuesta MulKI ofrece un enfoque eficaz para el aprendizaje continuo de Modelos de Visión y Lenguaje.
    • MulKI integra con éxito el conocimiento emulando los procesos de aprendizaje humano, superando las limitaciones de los métodos existentes.
    • Este trabajo muestra una gran promesa para adaptar los VLM a entornos de datos dinámicos y en evolución.