Powered by OpenAIRE graph
Found an issue? Give us feedback
image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/ Recolector de Cienci...arrow_drop_down
image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/
Recolector de Ciencia Abierta, RECOLECTA
Bachelor thesis . 2023
License: CC BY NC ND
addClaim

Redes neuronales bayesianas

Authors: Fornet Martín, Pablo;

Redes neuronales bayesianas

Abstract

Las redes neuronales modernas son una herramienta que permite resolver una gran variedad de problemas y retos en el ámbito de la inteligencia artificial. Sin embargo debido a que operan como cajas negras, la incertidumbre de sus predicciones es difícil de cuantificar. El paradigma bayesiano ofrece herramientas para cuantificar la incertidumbre asociada a las predicciones de una red neuronal. La principal diferencia del enfoque bayesiano es la marginalización, en vez de seleccionar una única configuración de parámetros. La marginalización, que consiste en tener en cuenta varias configuraciones de parámetros que se ajustan a los datos de entrenamiento puede mejorar la precisión de la red neuronal, pero sobre todo permite aproximar mejor la incertidumbre de la predicción. En este trabajo explicamos una visión general de cómo funciona y se implementa una red bayesiana y las principales ventajas que estas presentan.

Keywords

Bayes, Incertidumbre, Informática (Informática), Conjuntos de redes neuronales, Red neuronal estocástica, Uncertainty, Deep ensembles, Red neuronal bayesiana, Stochastic neural network, Bayesian deep learning, Marginalización, Distribución a posteriori, 004(043.3), Marginalization, Posterior distribution, 33 Ciencias Tecnológicas

  • BIP!
    Impact byBIP!
    selected citations
    These citations are derived from selected sources.
    This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
    0
    popularity
    This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network.
    Average
    influence
    This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
    Average
    impulse
    This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network.
    Average
Powered by OpenAIRE graph
Found an issue? Give us feedback
selected citations
These citations are derived from selected sources.
This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
BIP!Citations provided by BIP!
popularity
This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network.
BIP!Popularity provided by BIP!
influence
This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
BIP!Influence provided by BIP!
impulse
This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network.
BIP!Impulse provided by BIP!
0
Average
Average
Average
Green