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

Depth Perception and Spatial Vision01:15

Depth Perception and Spatial Vision

1.8K
Depth perception is the ability to perceive objects three-dimensionally. It relies on two types of cues: binocular and monocular. Binocular cues depend on the combination of images from both eyes and how the eyes work together. Since the eyes are in slightly different positions, each eye captures a slightly different image. This disparity between images, known as binocular disparity, helps the brain interpret depth. When the brain compares these images, it determines the distance to an object.
1.8K
High-Level and Low-Level Awareness01:19

High-Level and Low-Level Awareness

618
Controlled processes in human consciousness represent high-alert mental states where individuals deliberately focus their attention on achieving specific goals. Controlled processes can be seen in situations like mastering new technology, where a person might become so absorbed that they ignore surrounding distractions. Such processes involve selective attention, requiring one to concentrate on particular elements of experience while disregarding others. These are governed by executive...
618
Machines: Problem Solving II01:30

Machines: Problem Solving II

632
Machines are complex structures consisting of movable, pin-connected multi-force members that work together to transmit forces. Consider a lifting tong carrying a 100 kg load. It comprises movable sections DAF and CBG linked together with member AB.
632
Machines: Problem Solving I01:22

Machines: Problem Solving I

670
A toggle clamp is a mechanical device commonly used for holding and clamping objects in various applications, such as woodworking, metalworking, and assembly operations. Consider a toggle clamp subjected to a force of 200 N at the handle. The vertical clamping force can be calculated, provided the dimensions of the toggle clamp are known.
The toggle clamp system is a machine structure consisting of movable, pin-connected multi-force members that form a stabilized system to transmit forces. The...
670
Modeling and Similitude01:12

Modeling and Similitude

598
Scaled modeling is a fundamental technique in engineering, enabling the study of large and complex systems by creating smaller, manageable replicas that recreate critical characteristics of the original. In hydrology and civil infrastructure, for example, scaled models of dams help analyze water flow, turbulence, and pressure. This method allows for accurate predictions of real-world behavior within a controlled environment, significantly reducing the cost and time involved in full-scale...
598
Gestalt Principles of Perception01:21

Gestalt Principles of Perception

1.0K
Gestalt principles provide a framework for understanding how humans perceive objects as unified wholes within their context. These principles are essential in explaining the cognitive processes that make sense of complex visual stimuli by organizing them into coherent groups. One fundamental principle is proximity, which posits that objects located close to each other are perceived as a collective group. For instance, when dots are positioned near one another, the visual system interprets them...
1.0K

También podría leer

Artículos Relacionados

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

Ordenar por
Same author

Towards robust foundation models for digital pathology.

Nature communications·2026
Same author

Beyond attention heatmaps: How to get better explanations for multiple instance learning models in histopathology.

Medical image analysis·2026
Same author

AI-based discovery of functional boundaries in the human brain from intraoperative electrophysiology.

medRxiv : the preprint server for health sciences·2026
Same author

Modeling attention and binding in the brain through bidirectional recurrent gating.

Nature communications·2026
Same author

Reply to Hu: Reasoning traces need not be faithful to account for the cost of human thinking.

Proceedings of the National Academy of Sciences of the United States of America·2026
Same author

Reply to Vankov et al.: Reasoning traces are linked to accuracy and capture key dimensions of problem complexity.

Proceedings of the National Academy of Sciences of the United States of America·2026
Same journal

Family of magnetic field-boosted superconductors in rhombohedral graphene.

Nature·2026
Same journal

What's the human cost of US research turmoil? A new film finds out.

Nature·2026
Same journal

Daily briefing: Ovaries start a second job after menopause.

Nature·2026
Same journal

Audio long read: Is the peptide craze backed by science? The promise behind the hype.

Nature·2026
Same journal

Scientists fight back against far-right plans to restrict academic freedom in Germany.

Nature·2026
Same journal

How AI can crack open the 'hidden curriculum' for neurodivergent students.

Nature·2026
Ver todos los artículos relacionados

Video Experimental Relacionado

Updated: Jan 11, 2026

Perceptual and Category Processing of the Uncanny Valley Hypothesis' Dimension of Human Likeness: Some Methodological Issues
07:34

Perceptual and Category Processing of the Uncanny Valley Hypothesis' Dimension of Human Likeness: Some Methodological Issues

Published on: June 3, 2013

17.9K

Alinear las representaciones visuales de máquinas y humanos a través de los niveles de abstracción

Lukas Muttenthaler1,2,3,4, Klaus Greff5, Frieda Born6,7,8

  • 1Google DeepMind, Berlin, Germany. lukas.muttenthaler@tu-berlin.de.

Nature
|November 12, 2025
PubMed
Resumen
Este resumen es generado por máquina.

Las redes neuronales profundas (DNN) a menudo no se generalizan como los humanos porque sus representaciones carecen de estructura jerárquica. Este estudio mejora los DNN con el conocimiento humano, mejorando su alineación con la cognición humana e impulsando el rendimiento del aprendizaje automático.

Más Videos Relacionados

Visualization Method for Proprioceptive Drift on a 2D Plane Using Support Vector Machine
07:05

Visualization Method for Proprioceptive Drift on a 2D Plane Using Support Vector Machine

Published on: October 27, 2016

9.6K
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

2.3K

Videos de Experimentos Relacionados

Last Updated: Jan 11, 2026

Perceptual and Category Processing of the Uncanny Valley Hypothesis' Dimension of Human Likeness: Some Methodological Issues
07:34

Perceptual and Category Processing of the Uncanny Valley Hypothesis' Dimension of Human Likeness: Some Methodological Issues

Published on: June 3, 2013

17.9K
Visualization Method for Proprioceptive Drift on a 2D Plane Using Support Vector Machine
07:05

Visualization Method for Proprioceptive Drift on a 2D Plane Using Support Vector Machine

Published on: October 27, 2016

9.6K
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

2.3K

Área de la Ciencia:

  • Inteligencia artificial
  • Ciencias cognitivas
  • Visión por computadora

Sus antecedentes:

  • Las redes neuronales profundas (DNNs) se utilizan cada vez más como modelos para el comportamiento humano y las representaciones neuronales.
  • Sin embargo, existen diferencias significativas entre la capacitación de DNN y el aprendizaje humano, lo que lleva a una mala generalización en los modelos.
  • Los modelos de visión actuales a menudo no logran capturar la organización jerárquica del conocimiento conceptual humano.

Objetivo del estudio:

  • Identificar y abordar el desajuste entre el conocimiento conceptual humano y las representaciones de DNN.
  • Desarrollar modelos de visión más alineados con los humanos que exhiban una mejor generalización y robustez.
  • Investigar métodos para infundir conocimiento humano en sistemas de inteligencia artificial (IA).

Principales métodos:

  • Entrenó a un maestro modelo para imitar los juicios humanos sobre la similitud conceptual.
  • Transfirió la estructura de representación alineada con el ser humano del modelo de maestro a los modelos de base de visión de última generación a través del ajuste fino.
  • Modelos evaluados en tareas de similitud utilizando juicios humanos a través de múltiples niveles de abstracción semántica.

Principales resultados:

  • Los modelos alineados con humanos demostraron aproximaciones más precisas del comportamiento humano y la incertidumbre.
  • El rendimiento mejoró en diversas tareas de aprendizaje automático, mostrando una mayor generalización y robustez fuera de la distribución.
  • Los modelos capturaron con éxito las abstracciones semánticas jerárquicas presentes en la cognición humana.

Conclusiones:

  • La integración del conocimiento humano en las RND crea una representación híbrida que se alinea mejor con los juicios cognitivos humanos.
  • Este enfoque conduce a sistemas de IA más robustos, interpretables y alineados con los humanos.
  • Infundir la IA con el conocimiento humano ofrece un camino prometedor hacia una inteligencia artificial más capaz y confiable.