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/ Universidade do Minh...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

Autoencoders lineares e autoencoders não lineares (ReLU)

Linear autoencoders and nonlinear autoencoders (ReLU)
Authors: Teixeira, Rui Pedro Silva;

Autoencoders lineares e autoencoders não lineares (ReLU)

Abstract

Este trabalho é dedicado ao estudo de autoencoders lineares, onde se destacam as suas ligações com a técnica PCA e com autoencoders não lineares, nomeadamente, usando a função de ativação ReLU. Ao longo desta dissertação, são demonstrados diversos resultados sobre esta temática, através de diversas simplificações e hipóteses adicionais. É ainda elaborada uma análise numérica que visa corroborar os resultados abordados ao longo do documento. Como principais destaques deste trabalho, pode-se enunciar o facto de que, para diversas bases de dados, é possível calcular uma solução ótima, ou seja, uma solução que atinge o valor mínimo que a loss function associada ao autoencoder consegue apresentar. Em particular, consideramos cenários com bases de dados de atributos não negativos, bem como a situação em que se assume que a base de dados é regular. E ainda de salientar a criação de novas propostas de algoritmos, em particular no contexto de autoencoders ReLU, que proporcionam muito boas aproximações das soluções ótimas com um baixo custo computacional em comparação aos tradicionais métodos de treino dos autoencoders com recurso as principais bibliotecas de Python.

Country
Portugal
Related Organizations
Keywords

Autoencoder linear, PCA, Linear autoencoder, Machine learning, Autoencoder ReLU

  • 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