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/
addClaim

Introducción al aprendizaje automático y al aprendizaje profundo

Authors: Méndez Corbacho, Ana;

Introducción al aprendizaje automático y al aprendizaje profundo

Abstract

En la actualidad, la Inteligencia Artificial es una disciplina científica ampliamente utilizada que está transformando diversos sectores. Una de las áreas más destacadas dentro de ella es el Aprendizaje Automático. Este Trabajo de Fin de Grado se centra en él y, en particular, en una de sus subramas de mayor interés actual: el Aprendizaje Profundo, que es especialmente eficaz en la resolución de problemas complejos. Comenzaremos el trabajo explorando diversos tipos dentro del Aprendizaje Automático y proporcionaremos una descripción destacando los algoritmos más utilizados en algunos de ellos. A continuación, nos centraremos en el Aprendizaje Profundo, que se basa en las redes neuronales artificiales, explicando las arquitecturas más comunes. Finalmente, presentaremos una serie de ejemplos para ilustrar el funcionamiento de algunos conceptos y algoritmos explicados a lo largo del trabajo. Estos ejemplos, algunos de los cuales consisten en implementaciones en Python de varios algoritmos y de redes neuronales, ayudarán a visualizar cómo se implementan estas técnicas en situaciones reales.

Currently, Artificial Intelligence is a widely used scientific discipline that is transforming various sectors. One of the most prominent areas within it is Machine Learning. This bachelor thesis focuses on this area, particularly on one of its most relevant current subfields: Deep Learning, which is especially effective in solving complex problems. We will begin the project by exploring various types within Machine Learning and providing a description highlighting the most commonly used algorithms in some of them. Next, we will focus on Deep Learning, which is based on artificial neural networks, explaining the most common architectures. Finally, we will present a series of examples to illustrate the functioning of some concepts and algorithms explained throughout the project. These examples, some of which consist of Python implementations of various algorithms and neural networks, will help visualize how these techniques are applied in real-world situations.

Universidad de Sevilla. Grado en Matemáticas

  • 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