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

Multi-input and Multi-variable systems01:22

Multi-input and Multi-variable systems

373
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...
373
Multicompartment Models: Overview01:14

Multicompartment Models: Overview

474
Multicompartment models are mathematical constructs that depict how drugs are distributed and eliminated within the body. They segment the body into several compartments, symbolizing various physiological or anatomical areas connected through drug transfer processes such as absorption, metabolism, distribution, and elimination.
These models offer a more comprehensive representation of drug behavior in the body than one-compartment models. They accommodate the complexity of drug distribution,...
474
Propagation of Action Potentials01:23

Propagation of Action Potentials

8.7K
The propagation of an action potential refers to the process by which a nerve impulse, or "action potential," travels along a neuron.
Neurons (nerve cells) have a resting membrane potential, with a slightly negative charge inside compared to outside. This is maintained by ion channels, such as sodium (Na+) and potassium (K+) channels, which control the flow of ions. When a stimulus, like a touch or a signal from another neuron, triggers the neuron, sodium channels open, allowing sodium ions to...
8.7K
Mechanistic Models: Compartment Models in Algorithms for Numerical Problem Solving01:29

Mechanistic Models: Compartment Models in Algorithms for Numerical Problem Solving

261
Mechanistic models play a crucial role in algorithms for numerical problem-solving, particularly in nonlinear mixed effects modeling (NMEM). These models aim to minimize specific objective functions by evaluating various parameter estimates, leading to the development of systematic algorithms. In some cases, linearization techniques approximate the model using linear equations.
In individual population analyses, different algorithms are employed, such as Cauchy's method, which uses a...
261
Observational Learning01:12

Observational Learning

791
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...
791
Model Approaches for Pharmacokinetic Data: Distributed Parameter Models01:06

Model Approaches for Pharmacokinetic Data: Distributed Parameter Models

223
Pharmacokinetic models are mathematical constructs that represent and predict the time course of drug concentrations in the body, providing meaningful pharmacokinetic parameters. These models are categorized into compartment, physiological, and distributed parameter models.
The distributed parameter models are specifically designed to account for variations and differences in some drug classes. This model is particularly useful for assessing regional concentrations of anticancer or...
223

También podría leer

Artículos Relacionados

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

Ordenar por
Same author

Linking Abundance and Activity of Ammonia-Oxidising Bacteria and Archaea in an Agriculturally Impacted First-Order Stream.

Environmental microbiology·2026
Same author

Versatile microbial community responsible for nitrate turnover in a carbonate aquifer in southwest Germany.

FEMS microbiology ecology·2026
Same author

<i>Desulfosporosinus</i> and <i>Acididesulfobacillus</i> dominate an acidophilic sulfate-reducing bacteria consortium during acid mine drainage bioremediation.

Applied and environmental microbiology·2026
Same author

Resistance Training Reshapes the Gut Microbiome in a Longitudinal 8-Week Intervention in Sedentary Adults.

Sports medicine - open·2026
Same author

The Metabolic State of <i>E. coli</i> Influences Fosfomycin Efficacy and Promotes Resistance Evolution.

ACS infectious diseases·2026
Same author

A donor-acceptor photosensitizer-catalyst dyad for light-driven nicotinamide hydrogenation.

Chemical science·2026

Video Experimental Relacionado

Updated: Jan 8, 2026

Decoding Natural Behavior from Neuroethological Embedding
08:00

Decoding Natural Behavior from Neuroethological Embedding

Published on: October 3, 2025

556

Modelos de Markov de Creencia Profunda para Inferencia POMDP

Giacomo Arcieri1, Konstantinos G Papakonstantinou2, Daniel Straub3

  • 1Institute of Structural Engineering, ETH Zürich, Zürich, 8093, Switzerland.

Neural networks : the official journal of the International Neural Network Society
|December 12, 2025
PubMed
Resumen

Este estudio presenta el Modelo de Markov de Creencia Profunda (DBMM), una novedosa arquitectura de aprendizaje profundo para la inferencia eficiente en problemas de Proceso de Decisión de Markov Parcialmente Observable (POMDP). Los DBMM permiten una toma de decisiones eficaz bajo incertidumbre, superando a los métodos existentes en entornos complejos.

Palabras clave:
CreenciasModelos de Markov ProfundosAprendizaje ProfundoGestión de InfraestructurasProcesos de Decisión de Markov Parcialmente ObservablesInferencia Variacional

Más Videos Relacionados

A Tactile Automated Passive-Finger Stimulator TAPS
19:44

A Tactile Automated Passive-Finger Stimulator TAPS

Published on: June 3, 2009

14.2K
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

2.2K

Videos de Experimentos Relacionados

Last Updated: Jan 8, 2026

Decoding Natural Behavior from Neuroethological Embedding
08:00

Decoding Natural Behavior from Neuroethological Embedding

Published on: October 3, 2025

556
A Tactile Automated Passive-Finger Stimulator TAPS
19:44

A Tactile Automated Passive-Finger Stimulator TAPS

Published on: June 3, 2009

14.2K
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

2.2K

Área de la Ciencia:

  • Inteligencia Artificial
  • Aprendizaje Automático
  • Aprendizaje por Refuerzo

Sus antecedentes:

  • Los Procesos de Decisión de Markov Parcialmente Observables (POMDP) son cruciales para la toma de decisiones secuencial bajo incertidumbre.
  • Los métodos de inferencia existentes para POMDP de alta dimensionalidad a menudo luchan con la escalabilidad y la falta de datos del estado de verdad fundamental.
  • El aprendizaje profundo ofrece potencial para modelar dinámicas complejas y no lineales inherentes a estos problemas.

Objetivo del estudio:

  • Introducir una novedosa arquitectura de aprendizaje profundo, el Modelo de Markov de Creencia Profunda (DBMM), para la inferencia eficiente de POMDP.
  • Desarrollar un enfoque agnóstico a la formulación del modelo para manejar entornos complejos, de alta dimensionalidad y parcialmente observables.
  • Permitir una inferencia de creencias robusta utilizando solo datos de observación, superando las limitaciones del cálculo exacto y los métodos de muestreo.

Principales métodos:

  • Desarrolló el Modelo de Markov de Creencia Profunda (DBMM), extendiendo los modelos de Markov profundos al marco POMDP.
  • Utilizó métodos de inferencia variacional para una inferencia de creencias eficiente directamente a partir de datos de observación.
  • Aprovechó las redes neuronales para inferir y simular dinámicas de sistemas no lineales, acomodando alta dimensionalidad y tipos de variables mixtas.

Principales resultados:

  • Los DBMM demostraron capacidades de inferencia eficientes y agnósticas a la formulación del modelo en problemas POMDP de referencia con variables discretas y continuas.
  • Los parámetros de la red neuronal se actualizaron de manera eficiente en función de la disponibilidad de datos, lo que permitió una adaptación dinámica.
  • Un agente de RL guiado por creencias de DBMM superó significativamente a las bases de referencia sin modelo, logrando un rendimiento casi óptimo en una tarea posterior.

Conclusiones:

  • Los DBMM proporcionan una solución eficaz para la inferencia de creencias en POMDP complejos, superando las limitaciones de escalabilidad y datos de los métodos tradicionales.
  • La capacidad de la arquitectura para inferir creencias permite la derivación de soluciones POMDP efectivas.
  • Los DBMM muestran una utilidad práctica significativa, mejorando el rendimiento de los agentes de aprendizaje por refuerzo en escenarios de toma de decisiones desafiantes.