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/
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/
versions View all 3 versions
addClaim

Redes neuronales: entrenamiento y comportamiento

Authors: Bueno, Fernando;

Redes neuronales: entrenamiento y comportamiento

Abstract

El propósito de este trabajo es estudiar la respuesta de una Red Neuronal según cambios en sus diferentes atributos para el mismo conjunto de datos dado. Para ello utilizaré dos ejemplos concretos, con diferentes conjuntos de datos reales y diferentes tipos de Redes Neuronales en cada uno de ellos. En el primero, utilizaré el conjunto de datos “mnist” que consiste en un conjunto de fotografías dadas en las que se ven diferentes imágenes de números escritos a mano y la Red Neuronal intentará reconocer dicho número. Las imágenes tienen una resolución de 28x28 pixeles y los números van del 0 al 9. En el segundo, utilizaré un conjunto de datos de la web filmográfica IMDB, del cual se extraerán 25000 diferentes críticas de películas etiquetadas según el sentimiento de dicha crítica. Para el buen funcionamiento de la Red Neuronal y la agilidad del estudio, he puesto el límite máximo de palabras a analizar en 500. Para este último caso, utilizare una Red Neuronal Convolucional. Otra idea que haré ver más adelante es que, aunque ciertos tipos de Redes se usan más para ciertos tipos de conjuntos de datos, cualquier Red puede ser usada para cualquier tipo de datos. Por ejemplo, las Redes Neuronales Convolucionales se usan más a menudo para imágenes y en este trabajo lo haré al contrario.

Keywords

1207.03 Cibernética, Conjuntos de datos, 1203.04 Inteligencia Artificial, 004.032.26, Machine learning, Inteligencia artificial (Informática), Datasets, Redes neuronales, Cibernética matemática, Inteligencia artificial, Aprendizaje automático, Neural networks

  • 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
Related to Research communities