Video Experimental Relacionado
Updated: Sep 10, 2025

03:31
Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
Published on: December 15, 2023
635
Expansión recurrente de la red para el aprendizaje incremental en clase
IEEE transactions on neural networks and learning systems
|August 27, 2025
Resumen
La expansión recurrente de la red (RNE) mejora el aprendizaje incremental de clase (CIL) al conectar expertos en tareas, reducir parámetros y mejorar la utilización de características para la inteligencia de visión adaptativa.
Área de la Ciencia:
- Visión por computadora
- Aprendizaje automático
- Inteligencia artificial
Sus antecedentes:
- El aprendizaje incremental de clase (CIL) es crucial para la inteligencia de la visión adaptativa.
- Los métodos actuales de expansión de red (NE) se enfrentan a desafíos como la difusión de características, el crecimiento de parámetros, la confusión de características y el sesgo del clasificador.
Objetivo del estudio:
- Introducir una nueva estructura dinámica, la ampliación recurrente de la red (RNE), para hacer frente a las limitaciones de los métodos CIL existentes.
- Mejorar la utilización de las características y reducir la complejidad del modelo en CIL.
Principales métodos:
- La RNE propuesta establece la transferencia secuencial de características entre los expertos en tareas a través de un módulo compartido.
- Los nuevos expertos en tareas se ajustan en función de las características recibidas, evitando la difusión y centrándose en áreas clave.
- RNE emplea la compresión reemplazando a los expertos en tareas con versiones aligeradas y utiliza un clasificador desacoplado con generación de pseudo-características para mitigar la confusión y el sesgo.
Principales resultados:
- RNE reduce significativamente los parámetros mientras mantiene el rendimiento.
- El método alivia efectivamente la confusión de las características y corrige el sesgo del clasificador.
- Se ha logrado un rendimiento de última generación (SOTA) en los conjuntos de datos CIFAR-100, ImageNet-100, Food-101 e ImageNet-1K.
Conclusiones:
- RNE ofrece una solución efectiva para el aprendizaje incremental en clase al mejorar el manejo de características y la eficiencia del modelo.
- El enfoque propuesto demuestra un rendimiento superior tanto en escenarios CIL estándar como desafiantes.
Videos de Conceptos Relacionados
Associative Learning
569
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...
Classical conditioning, also known...
569
Observational Learning
310
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...
310
Generalization, Discrimination, and Extinction
784
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...
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...
784
Introduction to Learning
529
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...
In contrast to learned behaviors, unlearned behaviors such as crying, sexual...
529
Cognitive Learning
516
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...
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...
516
Neuroplasticity
752
Neuroplasticity reflects the brain's remarkable capacity to adapt and evolve, responding dynamically to learning, experiences, or injury by reorganizing its neural circuitry. This reorganization involves creating new neural connections and refining old ones through a series of biological processes that contribute to the brain's lifelong development and adaptability.
752