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/ Minerva. Repositorio...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

Redes neuronais artificiais e aplicacións

Authors: Vence Nogueira, Roi;

Redes neuronais artificiais e aplicacións

Abstract

No seguinte traballo presentarase unha introdución ás redes neuronais dende a perspectiva da aprendizaxe automática mediante a minimización do risco empírico. Darase unha noción dos conceptos fundamentais no ámbito da estatística como o sobreaxuste, o infraaxuste e algunhas técnicas de regularización para evitar o desbalance entre ambas. Posteriormente e dentro do marco anterior, darase unha introdución ás redes neuronais centrada na súa estrutura de grafo. Este marco permitirá establecer un elegante método para o cálculo de derivadas sobre a rede, que permitirá adestrala mediante métodos de descenso do gradiente. Ademáis disto, a xeneralidade da descripción gráfica da rede permite manipular a súa arquitectura de xeito moi aberto, permitindo a creación das redes convolucionais e indo máis alá do elemental perceptrón múltiple. Estas redes son, no estado da arte actual, das ferramentas máis punteiras para a visión por computador e o procesamento de imaxes, tarefas que serán o fío conductor dos conceptos presentados. En conxunto, pretendese dar unha introdución dende o rigor matemático ao mundo das redes neuronais e o aprendizaxe automático, tratando de conciliar a visión máis pura da estatística e a optimización coas técnicas máis avanzadas do ámbito da computación, cuxos resultados non están precedidos dunha teoría que os respalde.

Country
Spain
Related Organizations
  • 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